INDEX

Explanations

mentions of declarations, often related to legal or official contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "declare" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

lla

-0.66

»Ĵ

-0.66

Reply

-0.65

 Purg

-0.64

 Notting

-0.64

nesota

-0.64

 Ninth

-0.64

devices

-0.63

 Palestin

-0.62

 Pavilion

-0.62

POSITIVE LOGITS

 declare

1.16

 declares

1.07

 declaring

0.99

 declarations

0.99

 declared

0.87

 declaration

0.84

 proclaim

0.83

ignty

0.83

 proclaiming

0.81

 allegiance

0.78

Activations Density 0.007%

mentions of declarations, often related to legal or official contexts

instances of the word "declare" and its variations

No Comments

No Known Activations