INDEX

Explanations

specific brands or names related to entities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 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

 vostri

-0.40

 lavoratori

-0.40

 näytte

-0.40

 Beispiele

-0.39

 Anmeldung

-0.38

็จ

-0.38

 circonstances

-0.38

 Durchschnitt

-0.38

 gius

-0.38

WebControls

-0.37

POSITIVE LOGITS

 Biôgrafia

0.63

thâu

0.57

省市镇

0.57

 ब्रेकडाउन

0.55

رشف

0.55

FunctionFlags

0.49

 tango

0.49

:✨

0.47

цезда

0.47

 noDo

0.47

Activations Density 2.682%

specific brands or names related to entities in various contexts

No Comments

No Known Activations