INDEX

Explanations

specific proper nouns, particularly names of characters or entities in a fictional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

aarrggbb

-0.70

basicConfig

-0.68

isContained

-0.64

StreetMap

-0.62

BrowserModule

-0.61

Derbyniad

-0.56

parsedMessage

-0.56

 Мексичка

-0.56

 FormsModule

-0.56

oa̍t

-0.55

POSITIVE LOGITS

σθαι

0.68

 Majefty

0.60

SuccessListener

0.59

Portail

0.59

 pleaſure

0.58

 Préférences

0.57

™,

0.56

Occasion

0.56

ècie

0.54

 myſelf

0.54

Activations Density 0.166%

specific proper nouns, particularly names of characters or entities in a fictional context

No Comments

No Known Activations