INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

è¦ļéĨĴ

-0.79

fell

-0.73

 fused

-0.65

iled

-0.62

 polled

-0.62

 Gale

-0.61

 paragraphs

-0.61

çķ

-0.61

umped

-0.61

iling

-0.60

POSITIVE LOGITS

Reviewer

0.81

repair

0.74

anne

0.71

operator

0.68

odore

0.65

ipment

0.64

wr

0.64

essor

0.61

 uniqueness

0.60

Den

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.