INDEX

Explanations

mentions of advocacy-related terms

oai_token-act-pair · gpt-3.5-turbo

references to advocacy and related organizational activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

orah

-0.86

å£«

-0.81

agher

-0.79

xus

-0.73

ursed

-0.73

agers

-0.72

 Eucl

-0.69

puted

-0.69

ells

-0.68

etti

-0.67

POSITIVE LOGITS

 advocacy

0.94

 efforts

0.93

 outreach

0.84

 campaigns

0.84

 organizations

0.79

 effort

0.78

 groups

0.78

 coordinator

0.77

irtual

0.73

 Organizations

0.72

Activations Density 0.024%

mentions of advocacy-related terms

references to advocacy and related organizational activities

No Comments

No Known Activations