INDEX

Explanations

references to neurobiology and related terms

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

Not in Any Lists

No Comments

Negative Logits

SuccessListener

-0.95

ات

-0.86

).}

-0.85

cinated

-0.82

mallows

-0.80

digarh

-0.80

ancier

-0.78

 kanya

-0.76

)}$,

-0.75

 postId

-0.75

POSITIVE LOGITS

 neuro

0.90

Neuro

0.83

 Neuro

0.81

neuro

0.72

 McDermott

0.70

Mauro

0.69

URO

0.69

://

0.66

 Mauro

0.65

 forem

0.65

Activations Density 0.004%

references to neurobiology and related terms

No Comments

No Known Activations