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

clud

-0.71

 Thiel

-0.70

 Digest

-0.66

Nug

-0.66

 Tycoon

-0.65

 Genius

-0.64

 Starter

-0.64

 Virgin

-0.64

 Defin

-0.63

Vi

-0.63

POSITIVE LOGITS

warming

0.89

mingham

0.85

umbn

0.79

rha

0.75

ignt

0.75

vernment

0.73

wake

0.73

bledon

0.72

akeru

0.70

 recoil

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.