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

cious

-0.73

ames

-0.68

Ron

-0.66

utions

-0.63

 vain

-0.63

Reviewed

-0.62

Scientists

-0.62

vic

-0.60

 darling

-0.60

 Diesel

-0.60

POSITIVE LOGITS

phabet

0.82

ubb

0.81

ramid

0.79

itudinal

0.75

MpServer

0.73

ibaba

0.70

thora

0.69

amaz

0.69

EStreamFrame

0.68

 seiz

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.