INDEX

Explanations

images or mentions of various specific subjects

oai_token-act-pair · gpt-3.5-turbo

references to animals, particularly cats, and certain political figures or social issues

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reins

-0.71

 maintains

-0.68

Attempts

-0.64

ciplinary

-0.63

 CASE

-0.61

ç¥ŀ

-0.60

*/(

-0.58

 mainline

-0.56

 CentOS

-0.56

Marginal

-0.56

POSITIVE LOGITS

igraph

0.71

 graffiti

0.66

 silhou

0.63

 handwriting

0.63

 paintings

0.63

actly

0.60

phot

0.59

 cartoons

0.59

 drawings

0.58

ulpt

0.57

Activations Density 1.006%

images or mentions of various specific subjects

references to animals, particularly cats, and certain political figures or social issues

No Comments

No Known Activations