INDEX

Explanations

phrases expressing uncertainty or doubt

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

wait for it to dry

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

tokens that occur in questions—interrogative words and auxiliary function words signaling a question (e.g., what/is/for/to/mean).

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

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

 curiosidad

-0.31

ându

-0.30

 özg

-0.27

 dovol

-0.27

com

-0.27

is

-0.27

 transición

-0.26

 conformidad

-0.26

POSITIVE LOGITS

parsedMessage

1.08

+#+#

0.98

 Signalez

0.94

OGND

0.91

 EconPapers

0.87

хьтан

0.85

rungsseite

0.83

IntoConstraints

0.79

Autoritní

0.79

 kasarigan

0.79

Activations Density 0.654%

phrases expressing uncertainty or doubt

wait for it to dry

tokens that occur in questions—interrogative words and auxiliary function words signaling a question (e.g., what/is/for/to/mean).

No Comments

No Known Activations