INDEX

Explanations

locations and geopolitical terms related to health and medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 pulumi

-0.65

原始内容存档于

-0.59

 global

-0.57

 globales

-0.56

fromnode

-0.54

 getItemCount

-0.51

 australian

-0.49

global

-0.49

Hentet

-0.48

campista

-0.48

POSITIVE LOGITS

 suburbs

0.94

 region

0.90

 suburb

0.81

 cities

0.81

 mainland

0.80

 Selatan

0.78

 continent

0.77

 Territory

0.76

 metropolis

0.76

 province

0.76

Activations Density 0.426%

locations and geopolitical terms related to health and medical contexts

No Comments

No Known Activations