INDEX

Explanations

prepositions and phrases indicating relationships or connections between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GTCX

-0.53

entsch

-0.43

ScopeManager

-0.41

ElementException

-0.40

IntoConstraints

-0.39

nemo

-0.39

 تضيفلها

-0.38

semantics

-0.38

jMenuItem

-0.37

AutoScale

-0.37

POSITIVE LOGITS

 disponibilités

0.59

 חיצוניים

0.52

 autorytatywna

0.52

+#+#

0.50

:^(

0.50

лтемелер

0.50

 跳转至

0.47

kkelijk

0.47

Чтоб

0.43

 jsonify

0.42

Activations Density 0.569%

prepositions and phrases indicating relationships or connections between concepts

No Comments

No Known Activations