INDEX

Explanations

characters' names and descriptions in a narrative context

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

<start_of_turn> user

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

SequentialGroup

-0.57

ंदीखरीदारी

-0.56

Datuak

-0.53

 autorytatywna

-0.47

 setUsername

-0.45

:**

-0.42

KommentareTeilen

-0.41

cshtml

-0.40

 cellspacing

-0.40

culosis

-0.40

POSITIVE LOGITS

Życiorys

0.41

Хьажоргаш

0.40

 Jurí

0.39

 Camargo

0.39

Kons

0.37

ieteur

0.37

voerd

0.36

 wounded

0.36

 leading

0.36

 ghost

0.36

Activations Density 0.015%

characters' names and descriptions in a narrative context

<start_of_turn> user

No Comments

No Known Activations