INDEX

Explanations

phrases related to technical or formal terms

oai_token-act-pair · gpt-3.5-turbo

significant nouns and their contextual relevance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Hok

-0.63

Moz

-0.57

 Aden

-0.56

 Forbidden

-0.56

 Nicarag

-0.56

hess

-0.55

Hoy

-0.55

 Blossom

-0.55

 Moss

-0.54

isol

-0.53

POSITIVE LOGITS

ï¸ı

1.18

âĢ

1.07

Ì¶

0.92

 âĢ

0.91

Â¯

0.89

etheless

0.87

(@

0.85

[/

0.84

_.

0.83

Â¨

0.82

Activations Density 0.418%

phrases related to technical or formal terms

significant nouns and their contextual relevance

No Comments

No Known Activations