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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onut

-0.67

 Dwell

-0.67

IPM

-0.65

kefeller

-0.64

merce

-0.63

ousel

-0.62

 pandemonium

-0.62

look

-0.61

ollo

-0.61

doi

-0.60

POSITIVE LOGITS

âĶĢâĶĢâĶĢâĶĢ

0.85

farious

0.70

kees

0.68

itud

0.67

iannopoulos

0.66

iola

0.66

Current

0.64

é¾įå¥ĳå£«

0.62

union

0.60

 blah

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.