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

 Contra

-0.75

Field

-0.71

Person

-0.67

iton

-0.66

ãģĻ

-0.65

ILS

-0.63

 Carpenter

-0.63

ifa

-0.63

QB

-0.62

Oak

-0.61

POSITIVE LOGITS

awaru

0.82

accompan

0.74

ospels

0.74

strip

0.72

eeper

0.72

argo

0.71

 depress

0.70

omers

0.70

glomer

0.68

 helic

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.