INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

wcsstore

-0.79

GoldMagikarp

-0.73

hered

-0.72

 Flavoring

-0.71

nic

-0.69

ãĥª

-0.68

ifiable

-0.67

Label

-0.67

\",

-0.66

'';

-0.63

POSITIVE LOGITS

?]

0.72

 Quin

0.71

Lago

0.67

?)

0.65

????????

0.65

????

0.64

 Drain

0.62

 Doomsday

0.61

soon

0.60

heit

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.