INDEX

Explanations

words related to government actions and policies

oai_token-act-pair · gpt-3.5-turbo

references to government actions and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Niet

-0.79

 rumors

-0.76

 Laden

-0.74

 Bundy

-0.74

defense

-0.73

behavior

-0.73

TMZ

-0.72

Sie

-0.72

Defense

-0.72

Ble

-0.70

POSITIVE LOGITS

 legisl

1.44

 recognise

1.41

 emphas

1.27

 recognised

1.20

 organise

1.16

 undertake

1.15

 apologise

1.15

 endeavour

1.15

 envis

1.14

 authorised

1.13

Activations Density 0.273%

words related to government actions and policies

references to government actions and policies

No Comments

No Known Activations