INDEX

Explanations

phrases related to law enforcement and incarceration

oai_token-act-pair · gpt-3.5-turbo

mentions of jail or incarceration

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

 Nare

-0.75

FORE

-0.74

xit

-0.69

 Scotia

-0.66

NetMessage

-0.62

 livest

-0.62

 Investors

-0.62

chell

-0.61

 Illum

-0.61

yip

-0.61

POSITIVE LOGITS

broken

0.99

break

0.94

breaks

0.94

breakers

0.93

strap

0.91

house

0.91

breaking

0.87

rooms

0.83

alde

0.80

breaker

0.79

Activations Density 0.017%

phrases related to law enforcement and incarceration

mentions of jail or incarceration

No Comments

No Known Activations