INDEX

Explanations

references to rules and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 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

 venons

-0.87

mặt

-0.79

 contextLoads

-0.79

 resourceCulture

-0.78

 occupé

-0.77

 Houſe

-0.74

 houſe

-0.73

 zufolge

-0.73

Efq

-0.73

 Theſe

-0.72

POSITIVE LOGITS

 rule

1.32

Rule

1.20

 Rule

1.16

rule

1.14

 rules

1.10

 RULE

1.10

 ruled

1.09

 Rules

1.08

 RULES

0.95

RULE

0.94

Activations Density 0.114%

references to rules and regulations

No Comments

No Known Activations