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

å¥

-0.81

Neigh

-0.73

LAN

-0.72

Rated

-0.69

Virgin

-0.68

Roy

-0.67

Vict

-0.66

nu

-0.66

cho

-0.66

Flight

-0.66

POSITIVE LOGITS

 would

0.85

would

0.79

 unless

0.76

ogy

0.71

 endeavour

0.70

 envis

0.68

(\

0.68

iss

0.67

 disposed

0.66

epad

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.