INDEX

Explanations

phrases indicating instructions or steps to follow

oai_token-act-pair · gpt-3.5-turbo

instances of the character "L" in various contexts

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

enegger

-1.00

 mathemat

-0.96

 disadvant

-0.88

 vulner

-0.77

 adolesc

-0.74

 accomp

-0.74

 unnecess

-0.74

 condem

-0.70

 suspic

-0.69

 simultane

-0.68

POSITIVE LOGITS

ï¸ı

1.15

ship

0.93

cation

0.86

ution

0.79

sure

0.78

sand

0.77

east

0.75

own

0.75

glass

0.73

aria

0.73

Activations Density 0.057%

phrases indicating instructions or steps to follow

instances of the character "L" in various contexts

No Comments

No Known Activations