INDEX

Explanations

phrases related to advocating for or calling for action

oai_token-act-pair · gpt-3.5-turbo

instances of the word "have" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rift

-0.59

 wounding

-0.58

 backdrop

-0.58

laus

-0.57

catentry

-0.56

 Creep

-0.56

hill

-0.56

etter

-0.55

 Dough

-0.52

etting

-0.52

POSITIVE LOGITS

 been

0.98

 gotten

0.98

 recourse

0.91

gotten

0.86

 undergone

0.84

been

0.83

 eaten

0.81

 taken

0.79

 access

0.78

 seen

0.77

Activations Density 0.114%

phrases related to advocating for or calling for action

instances of the word "have" in various contexts

No Comments

No Known Activations