INDEX

Explanations

legal and judicial terms

oai_token-act-pair · gpt-3.5-turbo

references to legal cases and court-related discussions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sacrific

-0.86

oji

-0.73

arine

-0.71

 commands

-0.71

 behaviours

-0.69

 substitutes

-0.69

 embr

-0.68

units

-0.68

robe

-0.67

ctrl

-0.66

POSITIVE LOGITS

 unresolved

0.99

 moot

0.95

 Watergate

0.90

 filed

0.88

 unsolved

0.88

 litigation

0.86

 Prosecutor

0.83

EStreamFrame

0.83

 jurisd

0.83

 extradition

0.82

Activations Density 0.416%

legal and judicial terms

references to legal cases and court-related discussions

No Comments

No Known Activations