INDEX

Explanations

references to things or individuals with a negative reputation or are widely known for notorious actions

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "notorious" or "infamous"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

zyme

-0.78

lations

-0.77

ULTS

-0.72

strings

-0.71

eling

-0.70

cos

-0.69

pt

-0.68

planes

-0.68

plet

-0.68

hire

-0.68

POSITIVE LOGITS

 infamous

0.84

 offender

0.83

 metic

0.83

 notorious

0.82

 culprit

0.82

 dictator

0.77

ebin

0.75

 nickname

0.70

 dirty

0.69

 scourge

0.68

Activations Density 0.031%

references to things or individuals with a negative reputation or are widely known for notorious actions

mentions of the term "notorious" or "infamous"

No Comments

No Known Activations