INDEX

Explanations

terms related to seizures and epilepsy

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

StoryboardSegue

-0.77

Tink

-0.73

achau

-0.69

dirs

-0.68

 Grunde

-0.68

 Anders

-0.68

SuppressLint

-0.68

WriteAttribute

-0.68

cshtml

-0.66

 Richt

-0.64

POSITIVE LOGITS

 seizure

1.54

 seizures

1.51

 Seizures

1.48

 Seiz

1.33

 epilepsy

1.21

 Epilepsy

1.05

 epileptic

0.90

 epile

0.88

 seized

0.82

 seize

0.82

Activations Density 0.006%

terms related to seizures and epilepsy

No Comments

No Known Activations