INDEX

Explanations

legal and criminal-related terms and concepts

oai_token-act-pair · gpt-3.5-turbo

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

Rap

-0.76

Rot

-0.72

Aut

-0.71

iosyn

-0.70

via

-0.69

Occup

-0.69

umn

-0.68

erent

-0.68

obal

-0.68

ordable

-0.68

POSITIVE LOGITS

 syndrome

1.04

 Syndrome

0.75

âĦ¢

0.71

 fallacy

0.69

 ratio

0.66

 Ratio

0.65

("

0.61

 è£ıç

0.60

!,

0.59

Activations Density 0.456%

legal and criminal-related terms and concepts

No Comments

No Known Activations