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

Downloadha

-1.04

 Skydragon

-0.79

ertodd

-0.77

ument

-0.76

Ì¶

-0.76

AZ

-0.74

thumbnails

-0.73

urai

-0.69

 FORM

-0.67

strap

-0.67

POSITIVE LOGITS

iquette

0.72

accompan

0.66

aren

0.63

PN

0.62

idal

0.61

lled

0.61

LED

0.61

 Waterloo

0.60

ery

0.60

 neighbours

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.