INDEX

Explanations

words related to physical structures or objects, particularly those related to trees or nature

oai_token-act-pair · gpt-3.5-turbo

words and phrases that indicate communication or interaction

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

nown

-0.71

nces

-0.71

lihood

-0.63

 enqu

-0.61

)=(

-0.60

raints

-0.59

 ours

-0.58

 endeav

-0.58

terior

-0.58

 affili

-0.56

POSITIVE LOGITS

ï¸ı

0.68

Arcade

0.66

YING

0.65

Pain

0.64

Balt

0.63

éĸ

0.63

ãĤĬ

0.63

Writing

0.63

APE

0.63

water

0.61

Activations Density 0.399%

words related to physical structures or objects, particularly those related to trees or nature

words and phrases that indicate communication or interaction

No Comments

No Known Activations