INDEX

Explanations

phrases related to legal and political contexts

oai_token-act-pair · gpt-3.5-turbo

expressions of confusion or puzzlement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Osc

-0.88

 Rockefeller

-0.78

kefeller

-0.73

 Chandler

-0.72

 Eisenhower

-0.71

 Wright

-0.70

 Rhodes

-0.70

Roc

-0.70

 Hughes

-0.68

 Hank

-0.68

POSITIVE LOGITS

 âĢ

1.87

âĢ

1.60

âĢł

1.28

â

1.19

âĢİ

1.11

Â¶

1.08

ðĿ

1.06

â

1.05

Â§

1.03

ï¸ı

1.01

Activations Density 1.000%

phrases related to legal and political contexts

expressions of confusion or puzzlement

No Comments

No Known Activations