INDEX

Explanations

references to legal or familial relationships, specifically those involving "in-laws."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 multiple

-0.62

 समीक्षक

-0.62

 person

-0.59

mol

-0.58

 some

-0.57

ViewFeatures

-0.57

 Person

-0.57

)))

-0.56

fäl

-0.55

WebElementEntity

-0.54

POSITIVE LOGITS

law

1.14

Efq

1.02

 houſe

0.96

 pleaſure

0.95

 ſtate

0.93

 Anſ

0.93

 Conſ

0.90

 Houſe

0.90

 uſed

0.89

 purpoſe

0.89

Activations Density 0.008%

references to legal or familial relationships, specifically those involving "in-laws."

No Comments

No Known Activations