INDEX

Explanations

phrases enclosed in quotation marks indicating direct speech

oai_token-act-pair · gpt-3.5-turbo

phrases or quotations that express opinions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Ļ½

-0.64

icular

-0.61

ãĥ´ãĤ¡

-0.61

stant

-0.59

rament

-0.58

paren

-0.57

prise

-0.57

PP

-0.57

Sense

-0.56

itan

-0.56

POSITIVE LOGITS

/"

0.92

 remark

0.63

 whereby

0.61

 because

0.54

 referring

0.54

sic

0.54

Reply

0.52

 whereas

0.52

]:

0.52

--

0.51

Activations Density 0.104%

phrases enclosed in quotation marks indicating direct speech

phrases or quotations that express opinions or statements

No Comments

No Known Activations