INDEX

Explanations

statistical terms related to demographic and health data

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

followed by past tense verbs

np_acts-logits-general · gemini-2.0-flash

percentages and proportions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

enderror

-0.61

providedIn

-0.53

lizia

-0.49

AutoScaleMode

-0.49

 архивлан

-0.48

Похо

-0.48

 validés

-0.48

ConverterFactory

-0.48

 Dostupné

-0.47

 épis

-0.47

POSITIVE LOGITS

 accounted

1.89

 account

1.84

 accounts

1.75

 accounting

1.75

account

1.56

 Account

1.54

accounting

1.53

 ACCOUNT

1.52

Account

1.42

accounts

1.41

Activations Density 0.623%

statistical terms related to demographic and health data

followed by past tense verbs

percentages and proportions

No Comments

No Known Activations