INDEX

Explanations

proper nouns and names associated with locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 vectorielles

-0.42

 tazas

-0.38

 supplémentaire

-0.35

LEGGI

-0.34

 diaria

-0.34

 tjen

-0.34

 vectorielle

-0.34

 plantillas

-0.33

 Tourismus

-0.33

 cliquer

-0.33

POSITIVE LOGITS

UserScript

0.79

 informée

0.65

sizeCache

0.62

parsedMessage

0.57

CPtr

0.56

########.

0.55

 AppCompatTheme

0.54

⤹

0.54

 ब्रेकडाउन

0.53

recated

0.51

Activations Density 0.277%

proper nouns and names associated with locations and institutions

No Comments

No Known Activations