INDEX

Explanations

proper nouns ending in '-inder'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "binder."

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

Negative Logits

romy

-0.71

meric

-0.71

 tremend

-0.71

hovah

-0.70

Ĥİ

-0.70

eny

-0.68

akening

-0.67

ramid

-0.66

rity

-0.66

estic

-0.66

POSITIVE LOGITS

inder

1.27

 Singh

0.91

åĤ

0.79

meyer

0.78

gaard

0.78

holm

0.77

Proxy

0.75

anguage

0.73

ãĥĸ

0.71

inders

0.70

Activations Density 0.013%

proper nouns ending in '-inder'

occurrences of the word "binder."

No Known Activations