INDEX

Explanations

phrases related to legal sentences and crime

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal sentences and penalties

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

sonian

-0.90

NetMessage

-0.73

INC

-0.69

 Alic

-0.68

ãĤ¤ãĥĪ

-0.67

sie

-0.67

orp

-0.66

Klu

-0.66

erial

-0.66

earth

-0.66

POSITIVE LOGITS

 imprisonment

1.02

 imposed

0.95

 sentences

0.94

 incarceration

0.92

ishment

0.88

 sentence

0.88

 detention

0.87

 incarcerated

0.87

 inflicted

0.86

 awarded

0.86

Activations Density 0.071%

phrases related to legal sentences and crime

phrases related to legal sentences and penalties

No Comments

No Known Activations