INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 MacArthur

-0.76

 Kaufman

-0.74

 Lomb

-0.72

Buk

-0.70

 Friedman

-0.68

anan

-0.68

 Weiner

-0.67

Vas

-0.66

 Pett

-0.66

 Olson

-0.63

POSITIVE LOGITS

abouts

0.84

ource

0.80

ources

0.73

terms

0.73

hips

0.72

hops

0.72

peed

0.70

hens

0.69

 answ

0.69

details

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.