INDEX

Explanations

instances of negation regarding existence or occurrence

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

"there is/was" followed by "no/an"

np_acts-logits-general · gemini-2.0-flash

there is no/a/an/some

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 AssemblyCulture

-0.90

bewerken

-0.79

 itſelf

-0.73

SharedCtor

-0.72

 Shakspeare

-0.67

antMatchers

-0.67

GEBURTSDATUM

-0.67

 Cæsar

-0.65

Atoi

-0.64

PYX

-0.62

POSITIVE LOGITS

no

1.50

 plenty

1.10

1.03

 lots

0.95

an

0.94

 some

0.93

 room

0.84

 ample

0.82

NO

0.81

 also

0.80

Activations Density 0.239%

instances of negation regarding existence or occurrence

"there is/was" followed by "no/an"

there is no/a/an/some

No Comments

No Known Activations