INDEX

Explanations

descriptions of products or services and related information

oai_token-act-pair · gpt-3.5-turbo

topics related to historical surveys and reports

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

?".

-0.58

.")

-0.57

)."

-0.56

 unpredict

-0.55

 babys

-0.53

)—

-0.52

"—

-0.52

ability

-0.51

 cuff

-0.51

 allergic

-0.51

POSITIVE LOGITS

senal

0.70

ursday

0.61

yrinth

0.59

lance

0.57

itled

0.56

utenberg

0.56

ortium

0.54

inav

0.54

USS

0.54

ãĥķãĤ©

0.54

Activations Density 1.350%

descriptions of products or services and related information

topics related to historical surveys and reports

No Comments

No Known Activations