INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Expend

-0.77

 Paint

-0.75

Map

-0.73

 Advis

-0.71

 Painter

-0.71

ZA

-0.70

 princip

-0.66

 Merchants

-0.65

 Maps

-0.65

XT

-0.64

POSITIVE LOGITS

ail

0.77

ails

0.75

uries

0.75

 adolesc

0.73

isted

0.72

inous

0.72

usting

0.69

ahoo

0.67

idays

0.67

iculture

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.