INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 certific

-0.69

 archived

-0.65

 debunk

-0.63

 polymorph

-0.61

 arsen

-0.60

Orig

-0.58

Fact

-0.58

 cease

-0.57

Pug

-0.56

SU

-0.55

POSITIVE LOGITS

lihood

0.89

 heartbeat

0.76

ptin

0.75

ä½ľ

0.70

 Nights

0.69

kees

0.69

 Jinn

0.67

lich

0.67

izon

0.66

ulz

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.