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

 formats

-0.75

ears

-0.73

utch

-0.71

arget

-0.65

doi

-0.65

artifacts

-0.62

irds

-0.62

osal

-0.61

Format

-0.61

ingu

-0.61

POSITIVE LOGITS

 warr

0.68

 neglig

0.67

gered

0.66

 pest

0.64

 renovations

0.64

tyr

0.63

rolet

0.63

nton

0.63

 Mistress

0.63

>>>>>>>>

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.