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

 param

-0.70

 ethn

-0.67

 Param

-0.66

 biome

-0.64

 Mono

-0.64

inar

-0.63

 crochet

-0.63

 Apply

-0.61

 answer

-0.60

 monthly

-0.60

POSITIVE LOGITS

ä»£

0.86

ATS

0.81

ORK

0.81

ARS

0.79

ASC

0.73

Virgin

0.70

emet

0.70

OWS

0.69

inals

0.68

shaw

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.