INDEX

Explanations

terms related to specific entities and organizations

oai_token-act-pair · gpt-3.5-turbo

specific names and terms related to organizations, products, and events

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

gered

-0.52

quickShipAvailable

-0.52

 doubled

-0.52

unts

-0.51

)=(

-0.50

,,,,

-0.50

 ..........

-0.50

roximately

-0.49

 Hels

-0.49

[];

-0.49

POSITIVE LOGITS

onian

0.62

bernatorial

0.61

advertising

0.58

CLOSE

0.55

PATH

0.54

MET

0.51

ollywood

0.51

consumer

0.50

plet

0.50

artisan

0.50

Activations Density 0.973%

terms related to specific entities and organizations

specific names and terms related to organizations, products, and events

No Comments

No Known Activations