INDEX

Explanations

evaluative descriptors and comparisons related to quality and effectiveness

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

Comparative/superlative adjectives

np_acts-logits-general · gemini-2.0-flash

most, best, exactly, ideal

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.43

 iprot

-0.40

DIPSETTING

-0.38

 coast

-0.38

 Abdul

-0.35

 Rodolfo

-0.35

bibitem

-0.35

Trichloroethane

-0.35

REQUIRES

-0.35

coast

-0.34

POSITIVE LOGITS

Personendaten

0.58

 otomatig

0.52

 noDo

0.51

setupUi

0.47

galus

0.46

不是很

0.45

 nogal

0.45

bootstrapcdn

0.43

 regrettable

0.41

 mało

0.40

Activations Density 0.293%

evaluative descriptors and comparisons related to quality and effectiveness

Comparative/superlative adjectives

most, best, exactly, ideal

No Comments

No Known Activations