INDEX

Explanations

references to specific rules and regulations in legal or formal texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 AssemblyVersion

-0.94

enuine

-0.92

."</

-0.89

 Humphreys

-0.88

+</

-0.88

︎

-0.86

 Hartmann

-0.85

Cordialement

-0.84

 Madsen

-0.84

Personensuche

-0.84

POSITIVE LOGITS

 rules

1.83

 rule

1.74

 Rules

1.72

 Rule

1.67

 RULE

1.60

Rules

1.57

rules

1.54

 RULES

1.53

Rule

1.44

rule

1.37

Activations Density 0.065%

references to specific rules and regulations in legal or formal texts

No Comments

No Known Activations