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

etheless

-0.78

akuya

-0.78

secut

-0.76

bara

-0.75

ebus

-0.74

armac

-0.74

ulum

-0.70

acks

-0.70

ãĤ¢ãĥ«

-0.69

ammed

-0.69

POSITIVE LOGITS

Merit

0.71

 FIRST

0.69

 WARNING

0.69

ETF

0.69

PHI

0.66

Filename

0.66

 Subscribe

0.63

 NOTE

0.63

 mentor

0.61

 RIGHT

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.