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

 skelet

-0.77

theless

-0.76

Oct

-0.76

Und

-0.73

ULE

-0.73

 corrid

-0.72

aban

-0.70

AMP

-0.69

ãĥŁ

-0.69

pty

-0.68

POSITIVE LOGITS

 Cousins

0.77

 Brand

0.72

 Equipment

0.70

hold

0.69

 Member

0.68

 Neighborhood

0.66

 Riders

0.66

 Ruler

0.66

stocks

0.65

 Partner

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.