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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âķĲ

-0.79

 Hath

-0.71

ï¸

-0.69

!/

-0.68

externalActionCode

-0.68

 Surviv

-0.66

DH

-0.65

âĶĢâĶĢ

-0.65

 Mobility

-0.65

çĭ

-0.65

POSITIVE LOGITS

ictions

0.74

pointers

0.72

 batches

0.68

Ħ¢

0.68

 frequent

0.66

manent

0.66

 Painter

0.66

amer

0.64

omore

0.64

 memos

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.