INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

none

-0.71

umenthal

-0.69

kefeller

-0.68

uctor

-0.66

steel

-0.64

 lengths

-0.64

upper

-0.62

iquette

-0.62

kinson

-0.62

izons

-0.60

POSITIVE LOGITS

 accommodation

0.71

 Emmanuel

0.65

 Chrys

0.61

 Flam

0.60

 Fract

0.60

Geh

0.60

 Mosque

0.58

antage

0.58

é¾įå¥ĳå£«

0.58

gb

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.