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

iscovery

-0.76

 ILCS

-0.75

 flashbacks

-0.71

 Cipher

-0.68

onds

-0.68

Anonymous

-0.66

inational

-0.65

olars

-0.64

ulton

-0.63

 Pict

-0.63

POSITIVE LOGITS

ãĤ¨ãĥ«

0.69

 Stur

0.69

tery

0.69

âĨĳ

0.67

ifully

0.60

pick

0.60

cape

0.59

 else

0.59

esson

0.59

 inaug

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.