INDEX

Explanations

coding structures related to object and memory management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

PostInfinity

-0.54

OGND

-0.54

 onPostExecute

-0.48

IsPostBack

-0.47

 nakalista

-0.45

omitempty

-0.43

InjectMocks

-0.43

 betweenstory

-0.42

Datuak

-0.41

チール

-0.40

POSITIVE LOGITS

httphttps

0.50

 Wicidata

0.47

nerability

0.43

帖最后由

0.43

 numberOfRows

0.42

 disambiguazione

0.39



0.39

 sogget

0.38

 advis

0.38

gwt

0.38

Activations Density 0.376%

coding structures related to object and memory management

No Comments

No Known Activations