INDEX

Explanations

phrases related to political figures and officials

oai_token-act-pair · gpt-3.5-turbo

proper nouns, especially names and titles related to individuals and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 resil

-0.78

 unden

-0.67

 cumbers

-0.65

 elig

-0.61

 conflic

-0.60

 evasion

-0.59

 theoret

-0.59

 Palestin

-0.58

)=

-0.58

 capacitor

-0.57

POSITIVE LOGITS

Jr

1.21

III

0.99

 whom

0.97

Sr

0.95

udeau

0.94

ovich

0.89

enegger

0.88

who

0.86

vich

0.85

*.

0.84

Activations Density 0.296%

phrases related to political figures and officials

proper nouns, especially names and titles related to individuals and their roles

No Comments

No Known Activations