INDEX

Explanations

references to natural phenomena and concepts

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

"natural"

np_acts-logits-general · gemini-2.0-flash

natural state or category

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 CreateTagHelper

-0.97

endpush

-0.92

 AssemblyTitle

-0.84

<caption>

-0.82

 ***!

-0.82

SBATCH

-0.78

 كومونز

-0.78

Britannique

-0.74

AddTagHelper

-0.73

 embarazada

-0.73

POSITIVE LOGITS

 natural

1.02

 Natural

0.88

 NATURAL

0.85

 natur

0.83

NATURAL

0.82

natural

0.78

Natural

0.78

 Natur

0.78

NAT

0.77

nat

0.76

Activations Density 0.097%

references to natural phenomena and concepts

"natural"

natural state or category

No Comments

No Known Activations