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

ulpt

-0.68

uckland

-0.67

});

-0.65

aunders

-0.65

Sham

-0.65

yton

-0.65

.''.

-0.64

})

-0.63

idae

-0.63

killed

-0.63

POSITIVE LOGITS

ockets

0.65

eele

0.61

azeera

0.59

 nowhere

0.58

CHO

0.58

 directive

0.58

cheon

0.57

 curfew

0.57

 discont

0.57

bey

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.