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

 tremend

-0.94

 metic

-0.80

 skelet

-0.78

 livest

-0.75

ciating

-0.72

 occas

-0.71

ikuman

-0.71

 enthusi

-0.71

 lact

-0.71

erva

-0.71

POSITIVE LOGITS

dll

0.92

Reviewer

0.75

dress

0.75

Tokens

0.74

Prosecutors

0.74

 Signed

0.73

Types

0.72

Materials

0.72

ļéĨĴ

0.71

MSN

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.