INDEX

Explanations

words related to turmoil, upheaval, and conflict

oai_token-act-pair · gpt-3.5-turbo

words associated with instability and conflict

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

©¶æ

-0.99

iphate

-0.84

anguage

-0.83

bsite

-0.78

imates

-0.78

available

-0.76

ATURE

-0.74

PLIED

-0.74

ften

-0.74

flix

-0.73

POSITIVE LOGITS

 affairs

0.89

 adolesc

0.86

 fortunes

0.82

 traject

0.81

 tides

0.81

 circumstances

0.80

 circumstance

0.79

 relations

0.78

 turmoil

0.78

 waters

0.77

Activations Density 0.078%

words related to turmoil, upheaval, and conflict

words associated with instability and conflict

No Comments

No Known Activations