INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

EStreamFrame

-0.89

çĶ°

-0.86

çļ

-0.86

éĹĺ

-0.85

è£ħ

-0.85

Berry

-0.84

 cannabin

-0.84

ç·

-0.83

Merit

-0.82

SAN

-0.81

POSITIVE LOGITS

iven

0.70

oggles

0.69

shire

0.68

gment

0.68

 scept

0.68

ror

0.67

elling

0.66

 experiment

0.66

 multicultural

0.65

reating

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.