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

sie

-0.70

lined

-0.68

sha

-0.68

prev

-0.67

assembly

-0.65

minecraft

-0.65

@#&

-0.65

Dan

-0.64

lining

-0.63

undo

-0.62

POSITIVE LOGITS

redit

0.82

onder

0.71

igl

0.65

IPM

0.63

 airspace

0.62

ocol

0.60

ennes

0.60

 baggage

0.59

gging

0.59

 underwear

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.