INDEX

Explanations

the word "that" occurring frequently in the text

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

the word "that" in various contexts throughout the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

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

maxwell

-0.68

culosis

-0.66

agne

-0.63

ãĥĥ

-0.62

oses

-0.60

argon

-0.60

||||

-0.60

Textures

-0.59

Numbers

-0.59

imaru

-0.59

POSITIVE LOGITS

 afforded

1.04

 enjoyed

1.02

 undertaken

1.01

of

1.00

 produced

1.00

 pioneered

1.00

 achieved

0.98

 practiced

0.97

 contained

0.96

 employed

0.96

Activations Density 0.098%

the word "that" occurring frequently in the text

the word "that" in various contexts throughout the document

No Comments

No Known Activations