INDEX

Explanations

terms related to personal data protection and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ویکی‌پدیا

-0.72

StructEnd

-0.61

XmlType

-0.61

CodedInputStream

-0.61

DockStyle

-0.58

textAppearance

-0.58

íslu

-0.57

 newOwner

-0.56

 estekak

-0.56

iteracy

-0.56

POSITIVE LOGITS

 sensitive

1.41

 personal

1.40

personal

1.14

sensitive

1.13

 Sensitive

1.12

Personal

1.08

 Personal

1.08

 personally

1.07

Sensitive

1.04

 PERSONAL

1.00

Activations Density 0.293%

terms related to personal data protection and privacy policies

No Comments

No Known Activations