INDEX

Explanations

mentions of approvals and consent in a formal context

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

"Approved" or "approval"

np_acts-logits-general · gemini-2.0-flash

official approval

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Not in Any Lists

No Comments

Negative Logits

 personeel

-0.44

 Schreiber

-0.40

ISODE

-0.39

Partie

-0.39

 oraș

-0.38

 onderdelen

-0.38

 vlees

-0.38

 latin

-0.38

ensity

-0.37

isString

-0.37

POSITIVE LOGITS

 approval

1.93

 approved

1.88

 approve

1.85

 Approval

1.82

 approves

1.74

 Approved

1.73

approved

1.72

 Approve

1.72

Approved

1.67

Approval

1.67

Activations Density 0.098%

mentions of approvals and consent in a formal context

"Approved" or "approval"

official approval

No Comments

No Known Activations