INDEX

Explanations

conversational phrases indicating doubt or disagreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 الرياضيه

-0.58

 Komunikasi

-0.56

 desmotivaciones

-0.55

tagHelperRunner

-0.54

berdayakan

-0.53

Kjelder

-0.51

 plufieurs

-0.48

UnsafeEnabled

-0.47

actéristi

-0.47

 ainfi

-0.47

POSITIVE LOGITS

Ya

0.39

internalType

0.39

Ya

0.37

 lame

0.36

ya

0.36

Crom

0.36

Yes

0.34

 Crom

0.34

Yes

0.33

noz

0.33

Activations Density 0.838%

conversational phrases indicating doubt or disagreement

No Comments

No Known Activations