INDEX

Explanations

indications of privacy concerns and the discussion surrounding sensitive information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

ropoda

-0.57

rag

-0.49

 surla

-0.48

rage

-0.47

postcss

-0.46

'].'

-0.46

 Weiss

-0.44

っか

-0.44

RuleContext

-0.44

<<"

-0.44

POSITIVE LOGITS

 personal

1.82

 private

1.70

personal

1.61

Personal

1.55

private

1.51

 Personal

1.51

PERSONAL

1.43

 PERSONAL

1.43

 privato

1.39

 privata

1.37

Activations Density 0.185%

indications of privacy concerns and the discussion surrounding sensitive information

No Comments

No Known Activations