INDEX

Explanations

a variety of topics, sometimes technical, but it frequently gives somewhat higher activations to words relating to coding, software, and computer tools

oai_token-act-pair · gemini-2.0-flash

Generic text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

al

-0.39

have

-0.36

Have

-0.35

co

-0.35

Has

-0.35

啊

-0.34

民

-0.34

ind

-0.34

CP

-0.31

of

-0.31

POSITIVE LOGITS

SBATCH

0.93

 Theſe

0.83

 myſelf

0.82

 Италијани

0.82

SpringRunner

0.81

 himſelf

0.81

ſelf

0.81

 means

0.77

 Савезне

0.77

 itſelf

0.76

Activations Density 9.948%

a variety of topics, sometimes technical, but it frequently gives somewhat higher activations to words relating to coding, software, and computer tools

Generic text

No Comments

No Known Activations