INDEX

Explanations

terms related to the action of pulling in various contexts

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

pull out

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

CppMethod

-0.56

setVerticalGroup

-0.55

endregion

-0.52

 Matheson

-0.51

 intptr

-0.49

 فريبيس

-0.49

 initComponents

-0.49

 ***!

-0.48

 σο

-0.48

zwischen

-0.47

POSITIVE LOGITS

Pull

1.56

 Pull

1.56

 pull

1.52

pull

1.41

 PULL

1.40

PULL

1.30

 pulls

1.07

 Pulling

1.04

 pulling

1.00

Pulling

0.99

Activations Density 0.008%

terms related to the action of pulling in various contexts

pull out

No Comments

No Known Activations