INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

everal

-0.82

ordes

-0.82

icter

-0.81

izens

-0.77

iscons

-0.76

conservancy

-0.75

onto

-0.75

cade

-0.74

isphere

-0.70

alogue

-0.70

POSITIVE LOGITS

REF

0.79

 Lans

0.75

 Kinder

0.64

 Broad

0.63

 economics

0.63

 Finance

0.62

 Economics

0.62

 Malaysia

0.61

 Barg

0.60

fee

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.