INDEX

Explanations

cryptocurrency names and terms

oai_token-act-pair · gpt-3.5-turbo

variations of the word "spoon."

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

 crotch

-0.64

 chant

-0.59

 resemb

-0.58

ICAN

-0.58

 Scorp

-0.57

 prol

-0.56

 Beware

-0.55

 particle

-0.55

 Lerner

-0.54

 regress

-0.53

POSITIVE LOGITS

usters

0.88

ords

0.86

oard

0.85

eker

0.80

zyk

0.80

orst

0.78

Ã¼

0.78

atch

0.76

orde

0.76

ott

0.75

Activations Density 0.233%

cryptocurrency names and terms

variations of the word "spoon."

No Comments

No Known Activations