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

Mist

-0.77

LIA

-0.76

Wr

-0.75

olar

-0.73

SPONSORED

-0.72

veland

-0.72

Leary

-0.72

Climate

-0.71

å·

-0.70

å°Ĩ

-0.69

POSITIVE LOGITS

 pudding

0.76

pse

0.72

ļéĨĴ

0.71

 sexes

0.69

akedown

0.67

 sandwiches

0.66

nis

0.64

 nonex

0.63

 themselves

0.63

Ã¼r

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.