INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

aspx

-0.81

IDA

-0.73

mund

-0.73

tk

-0.73

weights

-0.72

Pool

-0.72

TEXTURE

-0.71

bucks

-0.69

quickShipAvailable

-0.69

TEXT

-0.68

POSITIVE LOGITS

 pardon

0.76

 restrain

0.71

ourage

0.68

uckland

0.67

 judge

0.66

 judges

0.64

lyak

0.62

 compensate

0.62

 Travel

0.61

 vain

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.