INDEX

Explanations

references to the letter "M" or terms starting with "M"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

AnchorStyles

-0.56

Durée

-0.52

bps

-0.46

requireNonNull

-0.40

mögens

-0.39

sg

-0.39

 contraire

-0.39

BeginInit

-0.38

ান

-0.38

àu

-0.37

POSITIVE LOGITS

Personensuche

0.51

 onPostExecute

0.44

 postIndex

0.42

 invokingState

0.39

 Infórmanos

0.38

eb

0.37

ArrowToggle

0.37

 saites

0.37

 للمعارف

0.37

 GoogleFonts

0.36

Activations Density 0.467%

references to the letter "M" or terms starting with "M"

No Comments

No Known Activations

references to the letter "M" or terms starting with "M"

No Comments

No Known Activations