INDEX

Explanations

references to roles and titles, particularly in academic or professional contexts

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

professions, roles, and education

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 '\\;'

-0.90

setVerticalGroup

-0.86

 AssemblyCulture

-0.82

 שוליים

-0.80

RegressionTest

-0.75

DockStyle

-0.73

 linkovi

-0.68

parsedMessage

-0.68

MLLoader

-0.67

 للمعارف

-0.66

POSITIVE LOGITS

 يتيمه

0.30

zusetzen

0.29

 principle

0.27

 applied

0.26

illard

0.26

mu

0.26

 Nerven

0.26

 beyond

0.25

nt

0.25

al

0.25

Activations Density 0.104%

references to roles and titles, particularly in academic or professional contexts

professions, roles, and education

No Comments

No Known Activations