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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Ranger

-0.75

MT

-0.72

 ranger

-0.67

RB

-0.63

 Staten

-0.62

 gearing

-0.62

RD

-0.60

 refugee

-0.60

 comfort

-0.59

POSITIVE LOGITS

Ü

0.86

MpServer

0.85

wcsstore

0.82

atically

0.78

*/(

0.77

licts

0.76

ILLE

0.75

âķĲ

0.75

 externalToEVAOnly

0.75

 attm

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.