INDEX

Explanations

possessive pronouns and their variations

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

possessive pronouns followed by nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 himſelf

-0.66

 avoient

-0.63

 kolye

-0.63

 étoient

-0.57

 föruts

-0.56

 propOrder

-0.56

 myſelf

-0.56

 Theſe

-0.55

ähteet

-0.55

gjenge

-0.54

POSITIVE LOGITS

in

0.81

In

0.75

InThe

0.59

 midst

0.57

IN

0.56

In

0.56

 regard

0.55

 dans

0.54

 nella

0.53

в

0.53

Activations Density 0.037%

possessive pronouns and their variations

possessive pronouns followed by nouns

No Comments

No Known Activations