INDEX

Explanations

technical terms or introductory phrases

oai_token-act-pair · gpt-3.5-turbo

instances of the word "introducing" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

avorite

-0.71

 Immunity

-0.68

 Mara

-0.68

 Fenrir

-0.64

 sleeper

-0.62

 Graves

-0.60

 Pend

-0.60

raint

-0.60

 Mankind

-0.60

 Pixie

-0.59

POSITIVE LOGITS

ctory

1.59

ctions

1.39

cing

1.32

ce

1.18

cÃ©

1.14

pta

1.14

gment

1.09

ctive

1.08

cer

1.05

ction

1.05

Activations Density 0.045%

technical terms or introductory phrases

instances of the word "introducing" and related variations

No Comments

No Known Activations