INDEX

Explanations

descriptive language about novels and literature

oai_token-act-pair · gemini-2.0-flash

fiction genres

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 esternos

-0.57

وصلات

-0.53

 estimés

-0.52

 telefónica

-0.50

HIRE

-0.49

 calciatore

-0.49

ulin

-0.47

Identyfik

-0.47

cita

-0.47

 berta

-0.47

POSITIVE LOGITS

 fiction

0.93

 fantasy

0.79

 novels

0.74

setVerticalGroup

0.72

 nonfiction

0.70

 mystery

0.68

 thriller

0.68

 Fiction

0.67

Fiction

0.66

 fictional

0.65

Activations Density 1.417%

descriptive language about novels and literature

fiction genres

No Comments

No Known Activations