INDEX

Explanations

references to characters and their attributes in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ⓘ

-0.58

出版年

-0.57

υμα

-0.54

 pleaſure

-0.52

 courtier

-0.51

bular

-0.51

ValueStyle

-0.51

tamment

-0.50

antism

-0.50

 Jonson

-0.49

POSITIVE LOGITS

 characters

0.85

 character

0.83

 personnage

0.82

 protagonist

0.82

 personaje

0.70

 personagem

0.70

 personaggio

0.69

 CHARACTERS

0.66

 karakter

0.66

 Characters

0.66

Activations Density 0.270%

references to characters and their attributes in narratives

No Comments

No Known Activations