INDEX

Explanations

positive and general descriptive words associated with creative works and their outcomes

oai_token-act-pair · gemini-2.0-flash

'a book'

np_token-act-pair-logits · gemini-2.0-flash

results

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 समीक्षक

-0.54

WriteAttribute

-0.50

 محفوظة

-0.49

mingen

-0.49

 beginnetje

-0.48

httphttps

-0.45

 réunis

-0.45

ску

-0.45

 ejer

-0.44

mtable

-0.43

POSITIVE LOGITS

WithIOException

0.65

 насеље

0.64

adaptiveStyles

0.63

новништво

0.60

modelBuilder

0.57

 highly

0.57

ValueGeneration

0.56

 vVar

0.56

Ligações

0.56

okia

0.55

Activations Density 1.516%

positive and general descriptive words associated with creative works and their outcomes

'a book'

results

No Comments

No Known Activations