INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 slopes

-0.76

 borders

-0.73

 Archdemon

-0.68

 circles

-0.66

 directions

-0.65

 instructions

-0.65

é¾įå¥ĳå£«

-0.64

 words

-0.64

 lyrics

-0.62

 valleys

-0.61

POSITIVE LOGITS

pload

0.76

eve

0.75

oslav

0.70

bang

0.69

mur

0.69

eat

0.68

rene

0.68

icter

0.68

ontent

0.68

arnaev

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.