INDEX

Explanations

numerical values and sequences indicative of measurements or statistics

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

Tokens followed by numbers

np_acts-logits-general · gemini-2.0-flash

numbers and citations

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

SaveChangesAsync

-0.95

Viited

-0.93

verwijspagina

-0.91

 Numerade

-0.90

DockStyle

-0.89

Espèce

-0.86

ConstraintMaker

-0.85

 cherchés

-0.82

 समीक्षाओं

-0.81

Aure

-0.80

POSITIVE LOGITS

 sinal

0.45

ิลป

0.44

 ucapan

0.43

 setLoading

0.42

енера

0.41

 счет

0.40

 creo

0.40

doi

0.40

 segnale

0.39

gefunden

0.39

Activations Density 0.553%

numerical values and sequences indicative of measurements or statistics

Tokens followed by numbers

numbers and citations

No Comments

No Known Activations