INDEX

Explanations

political statements and discussions

oai_token-act-pair · gpt-3.5-turbo

references to Congress and political sentiments

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

utterstock

-0.64

ptoms

-0.62

surprisingly

-0.59

sequent

-0.59

eaturing

-0.58

Vers

-0.57

 resulting

-0.56

phasis

-0.56

astical

-0.56

sequently

-0.55

POSITIVE LOGITS

 ..."

1.13

 âĢ¦"

1.13

%"

0.96

".[

0.89

";

0.88

 ______

0.86

"—

0.84

"?

0.84

'"

0.83

."[

0.81

Activations Density 0.875%

political statements and discussions

references to Congress and political sentiments

No Comments

No Known Activations