INDEX

Explanations

terms and phrases related to seizures and epilepsy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

colgroup

-0.74

WriteAttribute

-0.73

ScopeManager

-0.72

DeleteBehavior

-0.72

CPtr

-0.68

 opérateur

-0.67

DockStyle

-0.66

 BrowserModule

-0.66

 protoimpl

-0.65

writeFieldEnd

-0.65

POSITIVE LOGITS

 seizures

0.73

 epilepsy

0.72

 epileptic

0.71

 seizure

0.69

 epile

0.67

 Epile

0.59

 Epilepsy

0.55

 Seizures

0.51

 hippocampus

0.51

 Seiz

0.51

Activations Density 1.058%

terms and phrases related to seizures and epilepsy

No Comments

No Known Activations