INDEX

Explanations

phrases related to authorization or approval

oai_token-act-pair · gpt-3.5-turbo

exclamatory interjections or expressions of surprise and excitement

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

 unwanted

-0.75

 controvers

-0.75

 convenience

-0.73

 incorpor

-0.73

 overloaded

-0.72

ktop

-0.72

inent

-0.72

 inactive

-0.72

 associ

-0.71

 behavi

-0.70

POSITIVE LOGITS

ï¸ı

1.06

Â¯

0.95

Â°

0.87

âĶĢâĶĢâĶĢâĶĢ

0.86

âĶģ

0.86

âĻ¦

0.86

laughs

0.83

âĻ

0.81

ef

0.81

Activations Density 0.236%

phrases related to authorization or approval

exclamatory interjections or expressions of surprise and excitement

No Comments

No Known Activations