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

renheit

-0.77

 Democr

-0.75

ãĥĺ

-0.72

istor

-0.70

 inacc

-0.65

 horizont

-0.64

heit

-0.63

 falsehood

-0.63

 spherical

-0.63

sen

-0.62

POSITIVE LOGITS

emis

0.72

ourse

0.66

ĺħ

0.65

own

0.65

forward

0.63

APP

0.62

ipp

0.62

aucus

0.62

comings

0.62

ighth

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.