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

iasis

-0.82

ibur

-0.79

itutes

-0.74

strate

-0.70

£ı

-0.69

aughs

-0.68

olester

-0.67

wagen

-0.67

acan

-0.65

å§«

-0.65

POSITIVE LOGITS

jon

0.73

erest

0.69

rons

0.67

ppa

0.64

 juven

0.64

 Extrem

0.63

erving

0.61

rogen

0.61

 Hubble

0.60

 ensu

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.