INDEX

Explanations

mentions of legal terms related to post-conviction monitoring such as "probation" and "parole"

oai_token-act-pair · gpt-3.5-turbo

references to probation and related legal terminology

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

Dust

-0.69

-0.66

ãĤ¨

-0.64

Downloadha

-0.62

lycer

-0.62

bern

-0.62

rencies

-0.61

ffee

-0.61

ombies

-0.61

æŃ¦

-0.60

POSITIVE LOGITS

 probation

1.17

 parole

0.92

ary

0.86

 revocation

0.85

 confir

0.84

ally

0.81

urous

0.79

atory

0.75

ishment

0.73

 violation

0.73

Activations Density 0.013%

mentions of legal terms related to post-conviction monitoring such as "probation" and "parole"

references to probation and related legal terminology

No Comments

No Known Activations