INDEX

Explanations

prepositions indicating location or position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ंदीखरीदारी

-0.81

 Normdatei

-0.72

ModelSerializer

-0.70

 NSCoder

-0.64

 оригіналу

-0.62

SuppressMessage

-0.61

 Италијани

-0.59

TestingModule

-0.59

migrationBuilder

-0.59

!*\

-0.58

POSITIVE LOGITS

Hentet

0.59

example

0.47

Przypisy

0.44

 contrary

0.44

tamount

0.43

 dasar

0.43

ას

0.42

tle

0.42

 территории

0.41

 BACKGROUND

0.41

Activations Density 0.044%

prepositions indicating location or position

No Comments

No Known Activations