INDEX

Explanations

words related to actions or processes that involve either influencing others, causing change, or taking a stand

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hyde

-0.66

mare

-0.65

ingen

-0.58

itutional

-0.58

mallow

-0.57

 Shutterstock

-0.56

haar

-0.56

earable

-0.55

SourceFile

-0.55

omial

-0.55

POSITIVE LOGITS

 accordingly

0.85

 thereof

0.78

 importantly

0.77

 ensuing

0.75

 consequence

0.73

 consequently

0.71

 consequ

0.71

erity

0.67

pired

0.66

ĪĴ

0.66

Activations Density 0.208%

words related to actions or processes that involve either influencing others, causing change, or taking a stand

No Comments

No Known Activations