INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ovych

-0.84

crew

-0.84

walker

-0.77

ike

-0.69

loads

-0.69

tle

-0.68

strate

-0.68

walk

-0.68

hower

-0.64

idays

-0.63

POSITIVE LOGITS

ival

0.89

 seism

0.70

 Salvation

0.69

 Outbreak

0.66

 Paragu

0.65

 Lowe

0.65

 distingu

0.65

;;;;;;;;;;;;

0.65

qqa

0.63

©¶æ

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.