INDEX

Explanations

references to tragic events or situations

oai_token-act-pair · gpt-3.5-turbo

references to tragic events or circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aton

-0.89

ership

-0.81

gemony

-0.79

lav

-0.78

endum

-0.76

orney

-0.75

indal

-0.72

essee

-0.71

 retention

-0.71

urat

-0.69

POSITIVE LOGITS

 tragedies

0.88

 tragic

0.86

 tragedy

0.80

phans

0.78

 traged

0.78

 tragically

0.74

RIP

0.73

 unfolding

0.73

 unfold

0.72

 toll

0.71

Activations Density 0.021%

references to tragic events or situations

references to tragic events or circumstances

No Comments

No Known Activations