INDEX

Explanations

proper nouns related to geographical locations and landmarks

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

preceding place names

np_acts-logits-general · gemini-2.0-flash

place names and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

BeginInit

-0.69

NewUrlParser

-0.66

 незавершена

-0.65

matician

-0.64

 GetEnumerator

-0.63

casian

-0.61

]})

-0.61

RetentionPolicy

-0.59

]};

-0.59

Життєпис

-0.59

POSITIVE LOGITS

 village

0.76

 Village

0.74

 neighborhood

0.62

 Estate

0.61

 Farm

0.59

 paese

0.59

 paroisse

0.58

 station

0.57

 Road

0.56

 estate

0.56

Activations Density 0.357%

proper nouns related to geographical locations and landmarks

preceding place names

place names and features

No Comments

No Known Activations