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

able

-0.68

Critical

-0.67

Fail

-0.66

ATED

-0.64

 Staples

-0.64

 Balt

-0.64

DV

-0.62

INO

-0.60

 Baltic

-0.60

////////////////////////////////

-0.59

POSITIVE LOGITS

Downloadha

0.96

¬¼

0.93

omething

0.82

nir

0.81

hower

0.75

ae

0.72

ĺħ

0.72

£ı

0.72

HCR

0.71

umo

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.