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

 naked

-0.69

grab

-0.67

 Bans

-0.62

 grieving

-0.60

 minimized

-0.60

 perspect

-0.57

 Aust

-0.57

 advoc

-0.57

Faw

-0.57

 Watch

-0.57

POSITIVE LOGITS

ĸļ

0.74

actic

0.71

party

0.70

ument

0.70

wik

0.65

hemat

0.65

juven

0.65

 Notting

0.63

itate

0.63

success

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.