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

 endeav

-0.74

HIP

-0.70

 Downing

-0.65

opp

-0.64

Aeg

-0.63

Nos

-0.60

 Trident

-0.60

 Loch

-0.60

 opposite

-0.59

 aliases

-0.59

POSITIVE LOGITS

Tickets

0.80

Advertisements

0.78

Sales

0.76

Trivia

0.76

Month

0.74

opter

0.74

emetery

0.72

Micro

0.71

Buy

0.71

ayne

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.