INDEX

Explanations

phrases related to legal framework, including international law and regulations

oai_token-act-pair · gpt-3.5-turbo

references to legal concepts and laws

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

 Tate

-0.77

xit

-0.76

Dy

-0.64

Neh

-0.63

 Volunte

-0.63

ãĥĺ

-0.63

 throats

-0.63

icker

-0.62

rosse

-0.62

asted

-0.62

POSITIVE LOGITS

 enforcement

1.19

enforcement

0.97

making

0.94

 abiding

0.92

bending

0.90

makers

0.88

 Enforcement

0.87

compliance

0.85

 forb

0.84

suit

0.84

Activations Density 0.058%

phrases related to legal framework, including international law and regulations

references to legal concepts and laws

No Comments

No Known Activations