INDEX

Explanations

terms related to law enforcement and legal obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ModelExpression

-0.62

md

-0.46

 становника

-0.45

 EconPapers

-0.45

sizeCache

-0.45

UrlResolution

-0.44

Spa

-0.44

 Schi

-0.43

SA

-0.42

 Isol

-0.42

POSITIVE LOGITS

 enfans

0.63

 étoient

0.59

 avoient

0.58

ientras

0.57

 express

0.57

 miniaturka

0.55

 gră

0.54

 dieß

0.54

 zijne

0.52

 plufieurs

0.52

Activations Density 0.150%

terms related to law enforcement and legal obligations

No Comments

No Known Activations