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

achev

-0.91

GBT

-0.69

 vetoed

-0.67

Cu

-0.64

ãĥ¼ãĤ¯

-0.64

imir

-0.64

 pressing

-0.64

ISON

-0.63

INK

-0.63

emo

-0.63

POSITIVE LOGITS

uph

0.70

culture

0.67

 Depot

0.66

 Territory

0.63

 Unle

0.62

 extraord

0.60

rees

0.60

 tyres

0.60

 Hier

0.59

 Entreprene

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.