INDEX

Explanations

references to the concepts of "rest" and "remainder."

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

course of / remainder of

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

 ModelExpression

-0.43

 bParam

-0.40

__":

-0.32

%;">

-0.31

 heridas

-0.31

principalTable

-0.29

complexContent

-0.29

 Waray

-0.29

 tendencias

-0.28

TestTools

-0.28

POSITIVE LOGITS

Jeografia

0.60

ikusbot

0.59

oa̍t

0.57

webElementXpaths

0.57

şört

0.56

MessageOf

0.54

 ویکی‌پدی

0.54

palo

0.53

ResponseCode

0.53

ulongan

0.53

Activations Density 0.075%

references to the concepts of "rest" and "remainder."

course of / remainder of

No Comments

No Known Activations