INDEX

Explanations

references to plants and plant-related terminology

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

"plant" followed by various related words

np_acts-logits-general · gemini-2.0-flash

plant life and science

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

MemoryWarning

-0.92

WebVitals

-0.87

︎

-0.77

principalTable

-0.76

}],

-0.73

Santis

-0.73

rably

-0.72

ableness

-0.72

KURZBESCHREIBUNG

-0.72

derry

-0.70

POSITIVE LOGITS

life

0.57

 plants

0.55

 life

0.53

GHIJKLM

0.50

 species

0.48

ations

0.48

 baixa

0.47

Plants

0.46

 hosts

0.44

Life

0.44

Activations Density 0.114%

references to plants and plant-related terminology

"plant" followed by various related words

plant life and science

No Comments

No Known Activations