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

gravity

-0.71

earth

-0.69

units

-0.68

nw

-0.64

 Reloaded

-0.64

itionally

-0.64

olded

-0.62

ãĤ¼ãĤ¦ãĤ¹

-0.60

achev

-0.59

});

-0.58

POSITIVE LOGITS

sis

0.71

 Sinclair

0.69

 Nigel

0.66

rique

0.65

osate

0.64

 Derby

0.64

 Mercer

0.63

¿½

0.62

 styled

0.61

 Totem

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.