INDEX

Explanations

references to theft or missing items

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

ftagPool

-0.67

Begriffsklä

-0.54

jspx

-0.53

词

-0.52

oredCriteria

-0.51

 surla

-0.51

Rujukan

-0.50

Retry

-0.50

Rujuakan

-0.49

 kaarangay

-0.49

POSITIVE LOGITS

 away

0.78

 removal

0.62

 bort

0.61

 removed

0.60

 départ

0.58

removed

0.58

 removals

0.58

 remove

0.57

 Removal

0.56

 Removed

0.56

Activations Density 0.402%

references to theft or missing items

No Comments

No Known Activations