INDEX

Explanations

keywords or terms related to summarizing or reviewing content, often in a structured manner

oai_token-act-pair · gpt-3.5-turbo

references to recaps or summaries of events or content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

train

-0.76

 Breed

-0.66

 Mustang

-0.63

Wee

-0.63

Age

-0.63

 Laboratory

-0.59

erness

-0.57

 marriage

-0.57

Fish

-0.56

 Marriage

-0.56

POSITIVE LOGITS

ital

1.24

 recap

1.05

ocial

0.89

ilitation

0.88

itations

0.87

undown

0.86

itual

0.86

alon

0.86

rast

0.86

spective

0.85

Activations Density 0.013%

keywords or terms related to summarizing or reviewing content, often in a structured manner

references to recaps or summaries of events or content

No Comments

No Known Activations