INDEX

Explanations

questions and discussions about problem-solving and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 GenerationType

-0.62

 autorytatywna

-0.57

 CallOverrides

-0.57

addCriterion

-0.56

bewerken

-0.54

LookAnd

-0.54

Hauptartikel

-0.53

таратура

-0.52

 cherchés

-0.52

IntoConstraints

-0.51

POSITIVE LOGITS

 convince

0.70

 convincing

0.69

 balance

0.64

いかに

0.60

 balancing

0.60

 балан

0.58

 tricky

0.56

 persuading

0.56

如何在

0.55

 Balancing

0.55

Activations Density 0.488%

questions and discussions about problem-solving and decision-making processes

No Comments

No Known Activations