INDEX

Explanations

verbs and phrases indicating possession or attributes

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

Follows "has," "have," "had," or "got."

np_acts-logits-general · gemini-2.0-flash

has positive attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Javadoc

-0.58

 ब्रेकडाउन

-0.57

sona

-0.52

wpdb

-0.52

áky

-0.52

argout

-0.51

Réponse

-0.50

 respectively

-0.49

ContentLoaded

-0.49

?";

-0.49

POSITIVE LOGITS

 really

0.74

 lots

0.71

 LOTS

0.64

 REALLY

0.62

 plenty

0.60

 alot

0.60

 vraiment

0.60

 tons

0.59

 definitely

0.57

really

0.57

Activations Density 0.161%

verbs and phrases indicating possession or attributes

Follows "has," "have," "had," or "got."

has positive attributes

No Comments

No Known Activations