INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

-0.79

bidden

-0.76

 Converted

-0.75

omes

-0.72

ettings

-0.71

tainment

-0.70

cknow

-0.70

ication

-0.69

66666666

-0.68

akery

-0.67

POSITIVE LOGITS

 Papers

0.69

rose

0.65

 stall

0.62

 recalls

0.61

 limits

0.58

utra

0.58

papers

0.58

 representative

0.57

imeo

0.57

 causes

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.