INDEX

Explanations

the word "master" along with some context like "stroke," "race," "pieces," "mind," and "craftsman."

oai_token-act-pair · gpt-3.5-turbo

references to the term "master"

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

OPLE

-0.79

IDER

-0.74

DEN

-0.65

enegger

-0.64

 retirees

-0.64

tics

-0.62

hedon

-0.62

ople

-0.61

vernment

-0.61

gm

-0.60

POSITIVE LOGITS

pieces

1.39

mind

1.14

piece

1.14

class

0.98

stroke

0.96

fully

0.95

classes

0.95

work

0.91

ful

0.86

minded

0.85

Activations Density 0.021%

the word "master" along with some context like "stroke," "race," "pieces," "mind," and "craftsman."

references to the term "master"

No Comments

No Known Activations