INDEX

Explanations

mentions of the word "Little" in various contexts

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

"Little" followed by capitalized nouns

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 GenerationType

-0.71

 TextAppearance

-0.64

BibitemShut

-0.56

出版年

-0.54

euvres

-0.54

 Equinox

-0.53

 cheques

-0.53

 tyres

-0.52

ResumeLayout

-0.52

 iParam

-0.52

POSITIVE LOGITS

 Little

2.03

Little

1.99

 LITTLE

1.58

LITTLE

1.55

little

1.29

 little

1.05

 Peque

0.97

 Litt

0.87

 Kleine

0.83

小

0.81

Activations Density 0.004%

mentions of the word "Little" in various contexts

"Little" followed by capitalized nouns

No Comments

No Known Activations