INDEX

Explanations

references to legal actions or legal professionals, particularly prosecutors

oai_token-act-pair · gpt-3.5-turbo

mentions of prosecutors in relation to legal proceedings

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

yip

-0.76

oken

-0.72

lihood

-0.70

forward

-0.69

omach

-0.67

birth

-0.67

Wo

-0.66

wo

-0.65

opian

-0.65

patch

-0.64

POSITIVE LOGITS

 prosecutor

0.91

 indicted

0.89

 investigator

0.87

 prosecutors

0.86

heet

0.82

 investigating

0.82

 prosecuted

0.82

 proced

0.82

 allege

0.78

 subpoen

0.78

Activations Density 0.013%

references to legal actions or legal professionals, particularly prosecutors

mentions of prosecutors in relation to legal proceedings

No Comments

No Known Activations