INDEX

Explanations

phrases that indicate purpose or reason, particularly those beginning with "for."

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

make/provide for noun phrase

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

Viited

-0.51

Portale

-0.43

InjectAttribute

-0.40

lccn

-0.39

DAOImpl

-0.38

ExtendWith

-0.38

Varint

-0.37

Externí

-0.34

ese

-0.34

 punta

-0.33

POSITIVE LOGITS

addContainerGap

0.55

PageFactory

0.52

 occaf

0.52

éez

0.51

odend

0.49

 dortmund

0.48

Makes

0.48

 Makes

0.48

 Stirn

0.47

Made

0.47

Activations Density 0.010%

phrases that indicate purpose or reason, particularly those beginning with "for."

make/provide for noun phrase

No Comments

No Known Activations