INDEX

Explanations

references related to social media accounts or user handles

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

discrimination

-0.73

-0.70

rimination

-0.66

 conceal

-0.66

 barrier

-0.65

emb

-0.64

mental

-0.64

è¦ļéĨĴ

-0.63

iggurat

-0.63

und

-0.63

POSITIVE LOGITS

1.56

(@

1.28

1.19

"@

1.03

vs

1.00

(&

0.91

Vs

0.90

@@@@

0.89

@@

0.85

<@

0.84

Activations Density 0.096%

references related to social media accounts or user handles

references to specific individuals or communities

No Comments

No Known Activations