INDEX

Explanations

phrases related to quotes or statements made by notable figures

oai_token-act-pair · gpt-3.5-turbo

instances of the word "called" indicating statements or declarations made by individuals

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

Not in Any Lists

No Comments

Negative Logits

bilt

-0.85

inth

-0.82

=-=-

-0.75

 istg

-0.73

eland

-0.66

 unden

-0.64

ijn

-0.64

achusetts

-0.64

-------------

-0.64

Cub

-0.64

POSITIVE LOGITS

calling

0.91

call

0.91

 Call

0.86

 upon

0.85

 Calling

0.82

 calling

0.82

 Calls

0.78

Call

0.77

 calls

0.77

Activations Density 0.056%

phrases related to quotes or statements made by notable figures

instances of the word "called" indicating statements or declarations made by individuals

No Comments

No Known Activations