INDEX

Explanations

references to regulatory or legal rules and their classifications

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

+#+

-0.56

ervious

-0.55

+</

-0.53

 Hass

-0.53

 Amad

-0.52

 Abraham

-0.52

 restrictions

-0.52

?>

-0.52

 Hartmann

-0.52

 Hansen

-0.51

POSITIVE LOGITS

 Rule

2.70

 RULE

2.52

 rule

2.52

rule

2.44

Rule

2.41

RULE

2.05

 getRule

1.62

 règle

1.29

Regel

1.16

 правило

1.15

Activations Density 0.087%

references to regulatory or legal rules and their classifications

No Comments

No Known Activations