INDEX

Explanations

references to political and social controversies

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

followed by quantities or time periods

np_acts-logits-general · gemini-2.0-flash

many years of experience

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 NUKAT

-0.69

djangoproject

-0.65

有点

-0.62

 kics

-0.61

simpleType

-0.60

หน่อย

-0.59

ungkin

-0.59

 للاسماء

-0.58

 biraz

-0.58

 trochu

-0.57

POSITIVE LOGITS

 przecież

0.84

 hundreds

0.79

 centaines

0.77

 clearly

0.76

hundreds

0.75

 dozens

0.73

 countless

0.73

 thousands

0.72

thousands

0.72

 Hundreds

0.70

Activations Density 0.815%

references to political and social controversies

followed by quantities or time periods

many years of experience

No Comments

No Known Activations