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

 Riot

-0.67

 Neuroscience

-0.65

unning

-0.65

tsky

-0.63

 Tens

-0.62

Edited

-0.62

 econom

-0.62

****

-0.62

 Municipal

-0.61

 Scare

-0.60

POSITIVE LOGITS

market

0.72

touch

0.65

spring

0.65

¦

0.64

elvet

0.63

ocally

0.62

origin

0.59

 bloom

0.58

 Fedora

0.57

 mint

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.