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

cephal

-0.73

 segreg

-0.72

 hospitalized

-0.70

 associ

-0.67

stream

-0.67

 displaying

-0.66

 presenting

-0.66

 confined

-0.65

 drowning

-0.65

 convict

-0.64

POSITIVE LOGITS

UST

0.71

Dak

0.69

maximum

0.65

 Antiqu

0.65

Contract

0.65

OFF

0.64

KT

0.64

except

0.63

Registered

0.63

Publisher

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.