INDEX

Explanations

phrases highlighting the relationship between actions and their motivations or objectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

astéro

-0.63

antMatchers

-0.63

QMetaType

-0.62

writeValue

-0.56

DriverManager

-0.56

 Majefty

-0.56

 Eura

-0.56

 للمعارف

-0.55

 насељу

-0.54

 munt

-0.54

POSITIVE LOGITS

 WITHOUT

0.58

 WITH

0.57

WITH

0.57

الدراسه

0.56

 gewissen

0.56

 zonder

0.56

WITHOUT

0.55

senza

0.55

with

0.55

 föruts

0.54

Activations Density 0.350%

phrases highlighting the relationship between actions and their motivations or objectives

No Comments

No Known Activations