INDEX

Explanations

personal pronouns followed by a verb, typically in a conversational context

oai_token-act-pair · gpt-3.5-turbo

references to health insurance or healthcare-related topics

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

ËĪ

-0.56

iership

-0.56

 âĢº

-0.56

\":

-0.56

':

-0.55

 è£ıç

-0.54

âĦ¢:

-0.48

EGIN

-0.46

EU

-0.46

Published

-0.46

POSITIVE LOGITS

anwhile

0.69

 latter

0.66

 moreover

0.61

 furthermore

0.59

 disson

0.54

ogether

0.54

 therefore

0.54

 meanwhile

0.52

thus

0.49

Ļ½

0.49

Activations Density 1.988%

personal pronouns followed by a verb, typically in a conversational context

references to health insurance or healthcare-related topics

No Comments

No Known Activations