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

 Failed

-0.69

 Bench

-0.69

acher

-0.65

Lum

-0.62

ceiver

-0.62

kered

-0.61

 Haunted

-0.61

ilus

-0.60

 istg

-0.60

 unres

-0.58

POSITIVE LOGITS

 alliances

0.73

payment

0.67

 diversion

0.65

 footing

0.63

akin

0.63

 ceremonies

0.63

nell

0.61

site

0.61

":[{"

0.60

uri

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.