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

soever

-0.77

displayText

-0.72

Ĥª

-0.67

beit

-0.67

bery

-0.64

landers

-0.64

)].

-0.64

 sterling

-0.62

 Aires

-0.62

mberg

-0.62

POSITIVE LOGITS

Thumbnail

0.75

bringer

0.70

 Corrections

0.66

Images

0.66

utory

0.64

elist

0.63

umbnail

0.63

umerable

0.60

picture

0.60

ãĤĮ

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.