INDEX

Explanations

the character sequence "cul"

oai_token-act-pair · gemini-2.0-flash

culinary-related terms

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

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

Not in Any Lists

No Comments

Negative Logits

enumi

-0.72

openqa

-0.64

 endblock

-0.60

MemoryWarning

-0.59

allage

-0.52

UnknownFieldSet

-0.52

 onBind

-0.51

 defaultstate

-0.51

 ***!

-0.50

logrus

-0.48

POSITIVE LOGITS

 Redacción

0.55

 Reglamento

0.50

 Bryn

0.50

 cherchés

0.49

 damski

0.48

 CHtml

0.48

 ſmall

0.47

ائح

0.47

 jsPsych

0.47

 AppCompatTheme

0.47

Activations Density 0.443%

the character sequence "cul"

culinary-related terms

No Comments

No Known Activations