INDEX

Explanations

words and characters related to playing a game, possibly a video game, and specifically referring to "you"

oai_token-act-pair · gemini-2.0-flash

character-related terms

np_token-act-pair-logits · gpt-4o-mini

character

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Composable

-0.75

DockStyle

-0.63

ElementException

-0.59

GOTREF

-0.57

 препратки

-0.55

amaño

-0.55

 Réponses

-0.54

 okuyayım

-0.54

Cyfeiriadau

-0.54

moveToFirst

-0.53

POSITIVE LOGITS

 character

0.94

 characters

0.77

 Character

0.76

 hero

0.75

character

0.73

Character

0.69

 personagem

0.66

 personaje

0.65

 personaggio

0.64

 CHARACTER

0.64

Activations Density 2.938%

words and characters related to playing a game, possibly a video game, and specifically referring to "you"

character-related terms

character

No Comments

No Known Activations