INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

bm

-0.72

bors

-0.67

MC

-0.65

leton

-0.64

Interstitial

-0.64

lu

-0.64

Row

-0.63

ione

-0.62

TS

-0.62

 Downing

-0.62

POSITIVE LOGITS

 perspect

0.78

 chimpanzees

0.77

 Deng

0.72

 Omaha

0.70

 agon

0.69

 hostage

0.68

 helicop

0.67

 urgently

0.67

 weap

0.67

 drones

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.