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

 Skydragon

-0.73

 Bans

-0.72

 Scorp

-0.71

Sab

-0.71

 sail

-0.68

Scar

-0.68

Fal

-0.66

Shar

-0.66

 Sapp

-0.66

Shell

-0.66

POSITIVE LOGITS

cknowled

0.71

alogy

0.69

urate

0.66

thur

0.65

alog

0.64

 understatement

0.64

oner

0.63

cus

0.62

 Plaintiff

0.61

iste

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.