INDEX

Explanations

numeric values related to television ratings and viewer statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 resourceCulture

-0.64

__':

-0.56

__':

-0.48

HtmlAttribute

-0.47

jsii

-0.45

routeProvider

-0.44

nodoc

-0.43

ollectionView

-0.43

enterOuterAlt

-0.42

 screen

-0.42

POSITIVE LOGITS

Décès

0.47

 mukaan

0.44

 mikä

0.42

 näky

0.42

 kaikk

0.42

horabuena

0.42

Geplaatst

0.40

 compares

0.40

 grouping

0.40

 edged

0.40

Activations Density 0.331%

numeric values related to television ratings and viewer statistics

No Comments

No Known Activations