INDEX

Explanations

words related to actions of ingesting or consuming

oai_token-act-pair · gpt-3.5-turbo

words associated with various forms of sexual exploitation or harm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 magazine

-0.66

 plate

-0.59

 associations

-0.58

 design

-0.58

 mask

-0.58

 screw

-0.58

 handic

-0.57

 association

-0.57

 shop

-0.57

 podcasts

-0.56

POSITIVE LOGITS

ested

4.35

esting

2.98

ests

2.36

estation

2.19

est

1.74

EST

1.60

esters

1.38

esta

1.31

ester

1.21

uned

1.07

Activations Density 0.007%

words related to actions of ingesting or consuming

words associated with various forms of sexual exploitation or harm

No Comments

No Known Activations