INDEX

Explanations

percentages and numerical values, particularly related to changes or distributions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a transition or a goal, particularly with the word "to" followed by various objectives or changes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alogy

-0.69

 mosa

-0.68

ergic

-0.67

vo

-0.66

nostic

-0.66

fol

-0.65

cffffcc

-0.63

iHUD

-0.63

nexus

-0.63

hemat

-0.61

POSITIVE LOGITS

pload

0.99

 compensate

0.95

 expel

0.92

 commemorate

0.91

 celebrate

0.86

 conserve

0.84

pless

0.83

 abolish

0.81

 eliminate

0.80

 accommodate

0.80

Activations Density 0.134%

percentages and numerical values, particularly related to changes or distributions

phrases indicating a transition or a goal, particularly with the word "to" followed by various objectives or changes

No Comments

No Known Activations