INDEX

Explanations

prepositions and words after "the"

oai_token-act-pair · gemini-2.0-flash

proper nouns or specific names

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

events and tickets

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

IFrame

Link

Negative Logits

 ujednoznacz

-0.81

 InputDecoration

-0.80

TemporalType

-0.76

__":

-0.76

Rhestr

-0.76

Efq

-0.75

 TextAppearance

-0.73

তথ্যসূত্র

-0.72

 numberWith

-0.71

 disambiguazione

-0.71

POSITIVE LOGITS

EndContext

0.52

elstein

0.48

con

0.42

 Fast

0.42

 panel

0.42

row

0.41

 Cast

0.41

Row

0.40

phan

0.40

いに

0.39

Activations Density 1.971%

prepositions and words after "the"

proper nouns or specific names

events and tickets

No Known Activations