INDEX

Explanations

names and affiliations of individuals or entities, particularly in academic or professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.73

 GenerationType

-0.63

PhysRevLett

-0.62

人民共和国

-0.62

 getItemId

-0.61

Geplaatst

-0.59

 cdti

-0.58

__(/*!

-0.57

ItemBackground

-0.56

 Ugandan

-0.56

POSITIVE LOGITS

 Taiwan

1.09

Taiwan

0.92

 Taipei

0.88

 Taiwanese

0.79

 Formosa

0.77

 taiwan

0.72

 Tsai

0.69

Hsu

0.61

 Tait

0.60

Tai

0.60

Activations Density 0.074%

names and affiliations of individuals or entities, particularly in academic or professional contexts

No Comments

No Known Activations