INDEX

Explanations

the word "often" and its variants, indicating frequent occurrences or repetitions

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

"often"

np_acts-logits-general · gemini-2.0-flash

level of frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

الإنجليزية

-0.50

makeConstraints

-0.49

haway

-0.48

bsc

-0.46

 GenerationType

-0.46

 Савезне

-0.45

onInit

-0.45

 continuum

-0.44

 intptr

-0.44

OKA

-0.43

POSITIVE LOGITS

 genug

0.67

 times

0.66

times

0.64

Times

0.53

 enough

0.52

 TIMES

0.52

enough

0.50

 vezes

0.46

 genoeg

0.46

 referred

0.45

Activations Density 0.075%

the word "often" and its variants, indicating frequent occurrences or repetitions

"often"

level of frequency

No Comments

No Known Activations