INDEX

Explanations

numerical references to punishment or sentencing durations in years

oai_token-act-pair · gpt-3.5-turbo

long prison sentences

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

 VIDEOS

-0.96

 Collider

-0.89

ople

-0.78

acly

-0.71

achus

-0.66

Spawn

-0.65

inite

-0.65

atech

-0.65

Mom

-0.65

edia

-0.64

POSITIVE LOGITS

ago

1.23

 apiece

1.00

 probation

0.92

Ago

0.87

 imprisonment

0.84

long

0.78

 overdue

0.74

 incarceration

0.73

 olds

0.72

 consecut

0.72

Activations Density 0.087%

numerical references to punishment or sentencing durations in years

long prison sentences

No Comments

No Known Activations