INDEX

Explanations

titles of books, movies, and shows

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

Title case words after adjectives

np_acts-logits-general · gemini-2.0-flash

titles of movies and shows

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

 esetén

-0.83

verwijspagina

-0.77

NameInMap

-0.77

 ujednoznacz

-0.76

GEBURTSDATUM

-0.72

elemField

-0.67

setVerticalGroup

-0.66

StoreMessageInfo

-0.64

 "..\..\

-0.61

 natale

-0.59

POSITIVE LOGITS

 विश्वसनीयता

0.69

--)

0.59

getMenuInflater

0.57

 Store

0.57

amentals

0.56

CheckedChanged

0.54

SizeF

0.54

 McLaugh

0.54

 Files

0.54

oproject

0.53

Activations Density 0.246%

titles of books, movies, and shows

Title case words after adjectives

titles of movies and shows

No Comments

No Known Activations