INDEX

Explanations

instances of individuals coming forward with accusations or information

oai_token-act-pair · gpt-3.5-turbo

references to victims coming forward to share allegations or experiences of abuse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 ç¥ŀ

-0.86

otor

-0.85

Interstitial

-0.77

icio

-0.77

iculture

-0.76

 stabil

-0.76

icultural

-0.76

 stabilization

-0.73

hetics

-0.71

anguages

-0.71

POSITIVE LOGITS

 disclosures

1.39

 whistleblower

1.38

 confidential

1.34

 revelations

1.32

 allegations

1.31

 leaked

1.29

 disclosed

1.23

 disclosure

1.21

 testimonies

1.20

 dossier

1.19

Activations Density 1.519%

instances of individuals coming forward with accusations or information

references to victims coming forward to share allegations or experiences of abuse

No Comments

No Known Activations