INDEX

Explanations

references to sensitivity, particularly in relation to sensitive information or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 kasarigan

-0.71

webElementGuid

-0.59

 Мексичка

-0.56

 createdBy

-0.54

 dAtA

-0.54

 monog

-0.53

 disponibilités

-0.53

Rüyada

-0.52

 Verified

-0.52

 Italijanski

-0.52

POSITIVE LOGITS

 sensitive

0.59

 Miss

0.58

Miss

0.57

sensitive

0.57

 Continue

0.52

 find

0.50

miss

0.50

Continue

0.49

Sensitive

0.47

casting

0.46

Activations Density 0.109%

references to sensitivity, particularly in relation to sensitive information or contexts

No Comments

No Known Activations