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

 juven

-0.89

interstitial

-0.75

die

-0.68

asar

-0.66

atan

-0.66

 Whedon

-0.64

 Drawn

-0.63

ailability

-0.63

 Costume

-0.61

bane

-0.61

POSITIVE LOGITS

laws

0.73

bringer

0.64

atcher

0.64

 Painter

0.63

0.60

rob

0.59

 Sonia

0.57

 offsets

0.56

 Oblivion

0.55

oston

0.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.