INDEX

Explanations

proper nouns related to various entities, such as names of people and organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Ô

-0.78

halla

-0.67

orrow

-0.66

pton

-0.66

CTV

-0.65

 marrow

-0.65

çĦ

-0.64

ments

-0.63

ENCY

-0.62

kat

-0.61

POSITIVE LOGITS

rix

1.02

inav

0.80

ribute

0.79

xon

0.77

ribune

0.76

rogen

0.75

heon

0.70

erve

0.70

 Meier

0.70

ired

0.68

Activations Density 0.031%

proper nouns related to various entities, such as names of people and organizations

proper nouns, particularly names

No Comments

No Known Activations