INDEX

Explanations

technical terms and parameters related to code or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tahui

-0.62

führ

-0.55

elemField

-0.55

yo

-0.54

 Villanueva

-0.53

べて

-0.53

 typelib

-0.52

findpost

-0.51

RegressionTest

-0.50

blick

-0.49

POSITIVE LOGITS

 Мексичка

0.95

 GlobalKey

0.91

 StatefulWidget

0.78

^(@)

0.77

 useState

0.75

useState

0.74

moiselle

0.72

Efq

0.70

 tslint

0.70

 makeStyles

0.70

Activations Density 0.019%

technical terms and parameters related to code or programming

No Comments

No Known Activations