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

adv

-0.74

 appl

-0.73

den

-0.65

adv

-0.65

 SPACE

-0.64

 differs

-0.63

ockets

-0.62

,—

-0.62

obbies

-0.62

 embraces

-0.62

POSITIVE LOGITS

Reviewer

1.16

Hug

0.84

Scan

0.77

 Canaver

0.75

Gaza

0.74

Gas

0.73

ãĤ´ãĥ³

0.71

Ear

0.71

issance

0.70

Split

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.