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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hov

-0.81

 Gret

-0.77

ibilities

-0.73

iverpool

-0.72

 Advocate

-0.71

agos

-0.70

cean

-0.68

aug

-0.67

 Slovenia

-0.67

Balt

-0.66

POSITIVE LOGITS

 affili

0.65

yles

0.63

rera

0.63

 multic

0.61

 atom

0.60

 secondary

0.60

 imaginable

0.60

EStreamFrame

0.59

 steroid

0.59

 multit

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.