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

ahime

-0.80

avorite

-0.70

Choice

-0.68

hire

-0.65

AFTA

-0.65

mire

-0.62

 virginity

-0.62

 mercy

-0.62

emouth

-0.62

protection

-0.62

POSITIVE LOGITS

liv

0.71

 spec

0.69

endas

0.63

conom

0.62

dot

0.61

 trem

0.61

rep

0.61

Spec

0.60

ische

0.59

tem

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.