INDEX

Explanations

concepts and terminologies related to processes and practices in various fields

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

start_of_turn user

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

 ब्रेकडाउन

-0.77

 utafitiHapana

-0.64

 wireType

-0.59

Manbalar

-0.58

principalColumn

-0.56

Jereo

-0.55

 estekak

-0.54

 ProtoMessage

-0.53

XmlAccessorType

-0.52

сылкі

-0.52

POSITIVE LOGITS

huy

0.31

퀀

0.31

Den

0.30

readOnly

0.29

how

0.29

crity

0.28

 فع

0.28

 bied

0.28

 raises

0.28

INCIP

0.28

Activations Density 0.112%

concepts and terminologies related to processes and practices in various fields

start_of_turn user

No Comments

No Known Activations