INDEX

Explanations

terms related to awareness and understanding

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 Aung

-0.77

Presse

-0.76

 Marlowe

-0.73

Σε

-0.73

dut

-0.72

ellees

-0.69

pitre

-0.68

 Chwiliwch

-0.68

MigrationBuilder

-0.67

jazdu

-0.66

POSITIVE LOGITS

of

1.14

 aware

0.89

 Aware

0.89

Aware

0.83

']?>

0.82

]<<"

0.81

ardless

0.79

 dispose

0.79

 Beware

0.77

깐

0.75

Activations Density 0.519%

terms related to awareness and understanding

No Known Activations