INDEX

Explanations

instances of the word "to."

oai_token-act-pair · gpt-3.5-turbo

repeated prepositions and pronouns indicating actions or references in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Secondary

-0.65

 Hess

-0.63

 Kafka

-0.61

 Related

-0.58

Berry

-0.58

 Dickinson

-0.58

 Hogwarts

-0.57

 Abyssal

-0.56

ãģĻ

-0.55

 Applic

-0.55

POSITIVE LOGITS

pires

1.12

ifies

1.06

ked

0.89

ÃĥÃĤ

0.88

etheless

0.85

wrote

0.83

handled

0.82

stood

0.79

fort

0.77

ced

0.77

Activations Density 0.393%

instances of the word "to."

repeated prepositions and pronouns indicating actions or references in context

No Comments

No Known Activations