INDEX

Explanations

specific identifiers and demographic information related to individuals

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

Values after specific identifiers

np_acts-logits-general · gemini-2.0-flash

showing listed personal details

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

Sucesor

-0.69

 snippetHide

-0.58

IContainer

-0.57

坞

-0.56

 GetEnumerator

-0.56

ąp

-0.56

 Named

-0.56

 Focused

-0.56

árl

-0.55

󠁴

-0.55

POSITIVE LOGITS

 printed

0.73

 listed

0.66

 displayed

0.65

 exacte

0.59

 uveden

0.58

printed

0.57

 flashed

0.57

 imprimé

0.56

 affixed

0.56

 exacta

0.56

Activations Density 0.492%

specific identifiers and demographic information related to individuals

Values after specific identifiers

showing listed personal details

No Comments

No Known Activations