INDEX

Explanations

contexts involving mathematical definitions or operations related to sets and their elements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vě

-0.50

ابد

-0.45

-------------</

-0.43

WEBPACK

-0.43

ัก

-0.43

anti

-0.42

 General

-0.42

ICAN

-0.42

 usually

-0.41

Zir

-0.40

POSITIVE LOGITS

BeginContext

0.76

RegressionTest

0.75

rrggbb

0.73

Diweddarwch

0.72

脚注の使い方

0.68

AccessorTable

0.67

awtextra

0.66

modb

0.65

URLException

0.63

 <<<<<<<<<<<<<<

0.63

Activations Density 1.499%

contexts involving mathematical definitions or operations related to sets and their elements

No Comments

No Known Activations