INDEX

Explanations

mentions of political affiliations or actions

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names in the text

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

terday

-0.83

enegger

-0.78

anwhile

-0.63

oulos

-0.62

ierrez

-0.61

gomery

-0.61

 colle

-0.60

 destro

-0.60

gerald

-0.59

ãĥ¼ãĥĨ

-0.59

POSITIVE LOGITS

 Member

0.66

 Transfer

0.66

 Methods

0.63

 Profile

0.63

 Awoken

0.59

 Kills

0.58

 Crew

0.58

):

0.57

 Characters

0.57

 Pages

0.56

Activations Density 0.403%

mentions of political affiliations or actions

proper nouns and names in the text

No Comments

No Known Activations