INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pard

-0.79

olitical

-0.72

osph

-0.71

reth

-0.68

eters

-0.67

bringer

-0.67

roud

-0.67

 polled

-0.66

achev

-0.65

ilk

-0.64

POSITIVE LOGITS

 Flavoring

0.80

itud

0.74

alias

0.69

Sem

0.68

english

0.66

uay

0.65

 alias

0.65

idity

0.65

 millenn

0.64

idav

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.