INDEX

Explanations

references to restrictions on actions or behaviors

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

preposition 'on' followed by a noun phrase

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

المكان

-0.41

 jadx

-0.35

 ostavi

-0.34

 cercan

-0.34

"["

-0.31

낄

-0.31

 then

-0.31

 hype

-0.31

 interacted

-0.30

 worked

-0.30

POSITIVE LOGITS

KommentareTeilen

0.58

 utafitiHapana

0.55

 ProtoMessage

0.55

脚注の使い方

0.54

 FetchType

0.53

indeer

0.53

tableFuture

0.50

WebElementEntity

0.50

 snippetHide

0.50

batore

0.50

Activations Density 0.029%

references to restrictions on actions or behaviors

preposition 'on' followed by a noun phrase

No Known Activations