INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

iversary

-0.86

 neighbourhood

-0.67

skirts

-0.67

conservancy

-0.66

 elimination

-0.65

chin

-0.64

`.

-0.63

chal

-0.62

CHO

-0.62

 sabotage

-0.60

POSITIVE LOGITS

mone

0.72

MT

0.66

NRS

0.66

Present

0.65

ample

0.65

atio

0.64

akin

0.62

Proxy

0.62

Attach

0.62

ioxide

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.