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

ģĸ

-0.70

Ĥ

-0.70

ļ

-0.66

ľ

-0.66

ĻĤ

-0.65

 scouts

-0.64

ĸļ

-0.62

encer

-0.61

encers

-0.61

 prelim

-0.61

POSITIVE LOGITS

markets

0.73

 Cosponsors

0.72

DMV

0.72

lopp

0.71

lab

0.70

ween

0.69

weeney

0.68

anamo

0.66

liam

0.66

Western

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.