INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 GOODMAN

-0.76

 UPDATE

-0.72

Snake

-0.69

Wire

-0.69

'/

-0.64

-|

-0.64

WARE

-0.63

 Manip

-0.63

DI

-0.63

luence

-0.61

POSITIVE LOGITS

ciplinary

0.70

nings

0.68

akeru

0.65

ouston

0.65

gans

0.65

venants

0.64

nels

0.63

pires

0.63

 Sanct

0.63

pite

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.