INDEX

Explanations

short or descriptive words followed by nouns

oai_token-act-pair · gemini-2.0-flash

a/an

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Most

-0.54

 most

-0.50

-0.48

 المعيارى

-0.48

Most

-0.48

 Lots

-0.46

et

-0.45

 lotes

-0.45

-0.43

in

-0.43

POSITIVE LOGITS

Efq

1.34

 pleaſure

1.17

 Jefus

1.16

 purpoſe

1.15

ArrowToggle

1.12

 Monfieur

1.12

 Majefty

1.09

 Shakspeare

1.09

 itſelf

1.08

 Chriftian

1.06

Activations Density 1.540%

short or descriptive words followed by nouns

a/an

No Comments

No Known Activations