INDEX

Explanations

terms related to rules and compliance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Thacker

-0.48

orgon

-0.48

WebElementEntity

-0.48

<<(

-0.47

tetés

-0.45

敏

-0.45

 AppColors

-0.45

quin

-0.45

imenta

-0.43

 définitivement

-0.43

POSITIVE LOGITS

 compliance

1.86

 violation

1.75

 violations

1.62

 cumplimiento

1.61

compliance

1.59

 violated

1.57

 Compliance

1.55

 adherence

1.54

Compliance

1.52

 Violation

1.50

Activations Density 0.741%

terms related to rules and compliance in various contexts

No Comments

No Known Activations