INDEX

Explanations

mentions of negative incidents in society, such as harassment, violence, and tragedies

oai_token-act-pair · gpt-3.5-turbo

references to violence and conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Firstly

-0.84

\)

-0.75

 Firstly

-0.73

Appearance

-0.70

Very

-0.69

Primary

-0.69

,''

-0.69

Material

-0.67

.}

-0.67

operation

-0.67

POSITIVE LOGITS

 tsun

0.78

 cannibal

0.76

 poisoned

0.75

 coughing

0.73

 inexpl

0.72

 Kardashian

0.71

 disgr

0.69

 botched

0.69

 grizz

0.68

 assass

0.68

Activations Density 1.039%

mentions of negative incidents in society, such as harassment, violence, and tragedies

references to violence and conflict

No Comments

No Known Activations