INDEX

Explanations

mentions of the term "Bi" with various numerical values

oai_token-act-pair · gpt-3.5-turbo

mentions of "Bio" or related biomedical terminology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

MENTS

-0.83

lain

-0.81

âķĲâķĲ

-0.78

âķĲ

-0.78

ments

-0.76

å§«

-0.71

INGS

-0.67

 FIRE

-0.67

 sidx

-0.66

âĶĢâĶĢ

-0.66

POSITIVE LOGITS

omedical

1.18

otechnology

1.12

otech

1.08

ochem

1.06

Bi

1.02

ocide

1.01

omed

1.00

ographical

0.98

icides

0.95

ologically

0.95

Activations Density 0.006%

mentions of the term "Bi" with various numerical values

mentions of "Bio" or related biomedical terminology

No Comments

No Known Activations