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

è£ħ

-0.76

IELD

-0.69

RESULTS

-0.68

quickShipAvailable

-0.68

INFO

-0.67

GGGGGGGG

-0.67

Nem

-0.66

çīĪ

-0.66

æĥ

-0.65

ãĥĨ

-0.64

POSITIVE LOGITS

xual

0.78

eas

0.73

milo

0.72

semble

0.70

*/(

0.69

opus

0.68

itions

0.67

ullivan

0.66

ictions

0.66

 Runes

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.