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

OND

-0.72

 Verse

-0.71

ãĤ©

-0.70

urally

-0.69

 Gleaming

-0.67

ãģ®å®

-0.65

 Advertisement

-0.62

 Balloon

-0.61

ylon

-0.61

 Sheet

-0.61

POSITIVE LOGITS

0.94

0.93

0.90

0.89

0.85

0.84

much

0.79

0.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.