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

Untitled

-0.67

rio

-0.65

oct

-0.65

 WRITE

-0.64

 Eternity

-0.64

 Blazers

-0.62

ãĥ«

-0.62

 Valhalla

-0.62

 Fold

-0.62

Angelo

-0.60

POSITIVE LOGITS

xual

0.88

aminer

0.86

ategory

0.73

idav

0.71

emort

0.71

ainer

0.69

nown

0.69

 senses

0.68

ewitness

0.67

 estab

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.