INDEX

Explanations

sentences featuring the word "No."

oai_token-act-pair · gpt-3.5-turbo

the word "No" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iership

-0.91

ãĤ¼ãĤ¦ãĤ¹

-0.68

inese

-0.65

tnc

-0.65

rex

-0.65

ript

-0.64

ials

-0.64

isf

-0.63

endish

-0.63

(){

-0.63

POSITIVE LOGITS

xious

0.96

 kidding

0.95

 matter

0.94

zzle

0.91

etheless

0.90

 longer

0.89

 wonder

0.87

terday

0.85

 doubt

0.83

AH

0.82

Activations Density 0.064%

sentences featuring the word "No."

the word "No" in various contexts

No Comments

No Known Activations