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

Maker

-0.78

à¥

-0.77

 Citation

-0.71

à©

-0.69

 Instruct

-0.67

 Sect

-0.64

 Cake

-0.64

Drag

-0.63

×¨

-0.63

âĸ¬

-0.63

POSITIVE LOGITS

opian

0.84

roit

0.77

eful

0.74

redit

0.72

icrobial

0.69

iens

0.69

sonian

0.68

bum

0.66

acs

0.66

olic

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.