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

aun

-0.70

ÙĴ

-0.68

ommel

-0.66

 suffice

-0.66

 Horus

-0.66

alys

-0.63

Ô

-0.61

 Guth

-0.60

 awoken

-0.60

 incre

-0.59

POSITIVE LOGITS

EStreamFrame

0.69

ods

0.69

TeX

0.67

ODY

0.67

PHOTOS

0.66

reens

0.65

avier

0.64

Loading

0.64

uns

0.63

NRS

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.