INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Medicare

-0.72

Eps

-0.66

 Repair

-0.64

 Psychiatric

-0.62

Ð¼

-0.62

 Cyborg

-0.62

aepernick

-0.61

 BELOW

-0.61

Doctors

-0.61

ãĤª

-0.61

POSITIVE LOGITS

 cous

0.78

wcs

0.76

iazep

0.71

hes

0.69

 envelope

0.66

farious

0.66

iband

0.65

 spat

0.65

ket

0.64

uin

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.