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

seys

-0.78

edia

-0.74

ques

-0.70

verend

-0.70

nos

-0.69

Si

-0.68

Syd

-0.67

heid

-0.66

\-

-0.66

hemer

-0.66

POSITIVE LOGITS

ha

0.89

 Subtle

0.69

 Alto

0.66

 Community

0.62

Ide

0.58

 Highlander

0.58

 drop

0.56

 modifiers

0.56

 matter

0.56

imil

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.