INDEX

Explanations

syntax elements and programming-related tokens

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Preceding certain punctuation or special characters

np_acts-logits-general · gemini-2.0-flash

citations like WagnerBalbergKlein06

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

...

-0.68

‐

-0.60

....

-0.60

 ModelExpression

-0.52

mişti

-0.51

 فہرست

-0.51

</strong>

-0.51

',$

-0.49

......

-0.48

POSITIVE LOGITS

ſelf

0.97

ſelves

0.96

 autorytatywna

0.95

Efq

0.92

 itſelf

0.91

¦

0.89

 ſtate

0.89

 ſche

0.89

 pleaſure

0.88

 myſelf

0.85

Activations Density 3.314%

syntax elements and programming-related tokens

Preceding certain punctuation or special characters

citations like WagnerBalbergKlein06

No Comments

No Known Activations