INDEX

Explanations

pronouns and correlated verbs, with "I" being a particularly strong indicator

oai_token-act-pair · gemini-2.0-flash

would

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Filmografie

-0.83

 purpoſe

-0.79

 poffible

-0.78

<?

-0.77

felves

-0.77

Personendaten

-0.75

GEBURTS

-0.75

Tikang

-0.73

 pleaſure

-0.73

WindowConstants

-0.72

POSITIVE LOGITS

 would

2.34

would

1.90

 Would

1.73

Would

1.70

 WOULD

1.55

zou

1.07

 würde

1.06

 serait

1.05

 würden

1.05

 lenne

0.98

Activations Density 1.508%

pronouns and correlated verbs, with "I" being a particularly strong indicator

would

No Comments

No Known Activations