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

eger

-0.86

handled

-0.67

 Cellular

-0.66

edient

-0.65

¬¼

-0.64

ndra

-0.62

ls

-0.62

ł

-0.61

oxide

-0.60

 fashioned

-0.60

POSITIVE LOGITS

 =================================================================

0.70

 clarity

0.65

ylum

0.64

igate

0.63

utt

0.62

VK

0.61

0.60

 Kidd

0.60

inos

0.59

iversary

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.