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

 bios

-0.70

ovember

-0.65

 personality

-0.64

 gestation

-0.63

CST

-0.62

 analys

-0.62

 awareness

-0.60

arantine

-0.60

abies

-0.60

 conscious

-0.59

POSITIVE LOGITS

ppo

0.82

swick

0.76

iterranean

0.75

çĭ

0.73

Anonymous

0.71

TextColor

0.71

perty

0.71

esis

0.71

soon

0.70

orous

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.