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

 cler

-0.73

gyn

-0.66

 defer

-0.62

ricks

-0.61

fram

-0.60

 deem

-0.58

nec

-0.56

 Rober

-0.56

 redesign

-0.56

 haircut

-0.55

POSITIVE LOGITS

arnaev

0.82

izoph

0.82

oleon

0.68

Ħ¢

0.67

ratulations

0.66

ilus

0.66

ainer

0.65

enges

0.65

rimination

0.65

otti

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.