INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arth

-0.82

Ã¡n

-0.81

ibaba

-0.77

imir

-0.76

aho

-0.75

osate

-0.73

awaru

-0.73

ptin

-0.73

amine

-0.72

udo

-0.71

POSITIVE LOGITS

GET

0.68

 pleas

0.67

 surpass

0.66

 theater

0.65

 recorder

0.63

CAD

0.62

 Pentagon

0.62

 contr

0.61

 vocals

0.61

PU

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.