INDEX

Explanations

the word "usual" or variations of it

oai_token-act-pair · gpt-3.5-turbo

the term "usual" in various contexts

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

 Starship

-0.83

rift

-0.83

onics

-0.83

haw

-0.80

raped

-0.78

mented

-0.77

acus

-0.77

sten

-0.76

hani

-0.75

zik

-0.74

POSITIVE LOGITS

ITIES

0.87

 disclaimer

0.86

 suspects

0.81

 assortment

0.81

tenance

0.79

 caveats

0.79

 è£ıè¦ļéĨĴ

0.79

 partName

0.78

 disclaim

0.75

 mosqu

0.73

Activations Density 0.010%

the word "usual" or variations of it

the term "usual" in various contexts

No Comments

No Known Activations