INDEX

Explanations

words indicating confirmation or success

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

ending in "d"

np_acts-logits-general · gemini-2.0-flash

past tense verb endings

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 AssemblyCompany

-0.68

pecabe

-0.66

actéristi

-0.65

 فريبيس

-0.64

mpagne

-0.63

arangay

-0.63

 Signalez

-0.63

脚注の使い方

-0.61

 dignité

-0.59

 تضيفلها

-0.59

POSITIVE LOGITS

 seng

0.39

ة

0.39

的

0.39

us

0.38

ب

0.38

 Robinson

0.38

째

0.37

ment

0.37

ent

0.37

Activations Density 0.443%

words indicating confirmation or success

ending in "d"

past tense verb endings

No Comments

No Known Activations