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

});

-0.66

 duck

-0.61

 sexes

-0.60

cow

-0.57

":"","

-0.57

interstitial

-0.57

 grizz

-0.57

 ghosts

-0.56

 migr

-0.56

userc

-0.56

POSITIVE LOGITS

dyl

0.83

ghazi

0.76

inet

0.70

bey

0.69

lishes

0.69

rek

0.69

 Sabha

0.69

iti

0.68

ahime

0.67

kok

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.