INDEX

Explanations

phrases related to legal matters or representation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating representation or advocacy on behalf of others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

igmatic

-0.72

NetMessage

-0.63

floor

-0.63

igue

-0.62

quartered

-0.62

Definition

-0.62

esters

-0.60

oiler

-0.59

 crept

-0.59

acid

-0.58

POSITIVE LOGITS

 behalf

0.97

 Whole

0.76

 ours

0.69

 JUSTICE

0.67

 Yourself

0.67

 Nations

0.67

umbn

0.65

xon

0.63

enance

0.63

ffic

0.62

Activations Density 0.078%

phrases related to legal matters or representation

phrases indicating representation or advocacy on behalf of others

No Comments

No Known Activations