INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

lez

-0.78

lav

-0.70

 Pigs

-0.68

 Waves

-0.67

iners

-0.66

ursday

-0.65

hani

-0.64

voy

-0.64

 Scenes

-0.64

xual

-0.64

POSITIVE LOGITS

fit

0.78

opoly

0.66

 analogous

0.61

mental

0.61

 Pradesh

0.61

sty

0.60

 fashioned

0.59

console

0.59

central

0.58

glas

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.