INDEX

Explanations

expressions of identity and relationships among various entities

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

code and technical terms

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

CDCl

-0.41

 initComponents

-0.38

 &___

-0.35

RegressionTest

-0.35

__':

-0.34

 TestBed

-0.33

 announced

-0.32

luri

-0.32

 announcements

-0.32

dis

-0.31

POSITIVE LOGITS

oredCriteria

0.60

LookAnd

0.56

 itſelf

0.54

AddTagHelper

0.54

intios

0.54



0.52

delwed

0.52

 disambiguazione

0.51

Vidite

0.49

CloseOperation

0.48

Activations Density 0.750%

expressions of identity and relationships among various entities

code and technical terms

No Comments

No Known Activations