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

Desk

-0.72

WARE

-0.67

)]

-0.66

Captain

-0.64

 Sabb

-0.63

Queen

-0.63

hips

-0.62

Gender

-0.62

Ba

-0.61

esville

-0.61

POSITIVE LOGITS

 fateful

0.83

soever

0.82

 casts

0.78

eatures

0.77

cius

0.76

 sets

0.75

 morphed

0.70

 resulted

0.70

 enables

0.69

 pesky

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.