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

ropri

-0.67

person

-0.67

ela

-0.67

woman

-0.65

gal

-0.62

 Sounds

-0.62

ZI

-0.62

wife

-0.61

Si

-0.61

cow

-0.61

POSITIVE LOGITS

unker

0.71

ģĸ

0.69

 Thunderbolt

0.67

acers

0.67

 Seraph

0.66

leep

0.66

 Archangel

0.66

phrine

0.65

cipled

0.65

ĸļ

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.