INDEX

Explanations

terms related to legal concepts or regulations

oai_token-act-pair · gpt-3.5-turbo

references to legal principles and rules

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uliffe

-0.74

 ILCS

-0.68

asks

-0.65

Î³

-0.64

pi

-0.63

itent

-0.63

Task

-0.63

 grandchildren

-0.62

ptroller

-0.60

-0.59

POSITIVE LOGITS

 thumb

0.88

 precedence

0.75

clud

0.74

 Conduct

0.72

 propri

0.70

glers

0.69

 physics

0.65

restling

0.64

 legality

0.64

 logic

0.63

Activations Density 0.064%

terms related to legal concepts or regulations

references to legal principles and rules

No Comments

No Known Activations