INDEX

Explanations

verbs related to allowing or permitting actions to occur

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a sense of perseverance or encouragement

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

teness

-0.70

 Stri

-0.68

onday

-0.66

acea

-0.62

 Frequ

-0.61

terday

-0.60

ãĥĻ

-0.59

BA

-0.59

 Fixes

-0.58

 CARD

-0.58

POSITIVE LOGITS

 freely

1.08

 unim

0.85

 safely

0.84

 unchecked

0.83

querade

0.77

 cheaply

0.77

 unrestricted

0.74

 shine

0.74

 comfortably

0.74

 peacefully

0.71

Activations Density 0.118%

verbs related to allowing or permitting actions to occur

phrases that indicate a sense of perseverance or encouragement

No Comments

No Known Activations