INDEX

Explanations

references to data management and database operations

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

Capitalized words

np_acts-logits-general · gemini-2.0-flash

German prefixes and computer science terms

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

 Wikiseite

-0.79

 katholischen

-0.64

 ursprünglichen

-0.59

 mijne

-0.57

 zelve

-0.56

 nahilalakip

-0.56

 Menschheit

-0.55

 zwey

-0.55

RetentionPolicy

-0.55

 Betracht

-0.54

POSITIVE LOGITS

0.53

0.52

Es

0.52

Die

0.52

Be

0.52

Ver

0.51

0.50

0.49

Personensuche

0.49

Activations Density 0.046%

references to data management and database operations

Capitalized words

German prefixes and computer science terms

No Comments

No Known Activations