INDEX

Explanations

numerical values and references to quantities or measurements

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

Numbers followed by units of time or area

np_acts-logits-general · gemini-2.0-flash

numbers followed by time units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

曖昧さ回避

-0.58

->___

-0.54

homonymie

-0.49

 ExecuteAsync

-0.49

RepeatedField

-0.49

:')

-0.49

 giữa

-0.47

ukah

-0.47

'};

-0.46

Kreis

-0.46

POSITIVE LOGITS

AddHtmlAttribute

0.70

 labours

0.65

 evidences

0.65

gms

0.63

 folds

0.62

 sufferings

0.61

kgs

0.61

nos

0.61

 days

0.60

years

0.60

Activations Density 0.220%

numerical values and references to quantities or measurements

Numbers followed by units of time or area

numbers followed by time units

No Comments

No Known Activations