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

comings

-0.78

 Niet

-0.75

agascar

-0.67

leneck

-0.67

ilogy

-0.65

 Feeling

-0.64

 Kenyan

-0.64

 Downs

-0.63

à©

-0.63

ategory

-0.62

POSITIVE LOGITS

)'

0.78

ethical

0.69

)!

0.67

!--

0.65

ibur

0.65

 perman

0.64

)</

0.63

CONT

0.62

 uncond

0.62

 judgement

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.