INDEX

Explanations

phrases indicating limitations, disclaimers, or lack of guarantees regarding services or advice

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

Negation, often followed by a verb

np_acts-logits-general · gemini-2.0-flash

not replaced by

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

formal disclaimer and limitation language that negates capabilities, promises, rights, or responsibilities (e.g., “will not,” “does not,” “only,” “cannot”)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 lenker

-0.48

KommentareTeilen

-0.44

ueba

-0.42

COLN

-0.38

DeleteBehavior

-0.36

 improved

-0.36

edance

-0.35

Tikang

-0.35

发表于

-0.35

 Anbau

-0.34

POSITIVE LOGITS

httphttps

0.67

 createSprite

0.53

ſelves

0.50

VersionUID

0.45

URLException

0.44

 MainAxisSize

0.44

 Diſ

0.43

 secundario

0.42

 Normdatei

0.42

neither

0.42

Activations Density 0.449%

phrases indicating limitations, disclaimers, or lack of guarantees regarding services or advice

Negation, often followed by a verb

not replaced by

formal disclaimer and limitation language that negates capabilities, promises, rights, or responsibilities (e.g., “will not,” “does not,” “only,” “cannot”)

No Comments

No Known Activations