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

"},{"

-0.70

}}}

-0.68

 Geographic

-0.67

¤

-0.66

unta

-0.66

"},"

-0.65

cha

-0.63

Topic

-0.62

yll

-0.61

ja

-0.61

POSITIVE LOGITS

abal

0.73

ealing

0.73

elin

0.69

lication

0.69

 centr

0.68

bage

0.65

ifer

0.64

idation

0.63

 chall

0.62

Bloom

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.