INDEX

Explanations

mentions of arrests or activities related to law enforcement

oai_token-act-pair · gpt-3.5-turbo

references to arrests and related legal actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

issance

-0.77

ÃŁ

-0.75

pace

-0.70

 Remastered

-0.69

emonic

-0.68

ctory

-0.66

soDeliveryDate

-0.65

 embr

-0.64

 regener

-0.62

umen

-0.61

POSITIVE LOGITS

ees

1.06

 Warrant

1.03

 warrants

0.92

 warrant

0.91

able

0.88

eering

0.83

rained

0.82

ments

0.80

 arrest

0.79

ee

0.78

Activations Density 0.044%

mentions of arrests or activities related to law enforcement

references to arrests and related legal actions

No Comments

No Known Activations