INDEX

Explanations

cooking instructions or methods

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

serving food

np_acts-logits-general · gemini-2.0-flash

prepared to serve

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.91

AutoScaleMode

-0.78

IsContent

-0.73

-0.72

كويكب

-0.61

encodeWith

-0.61

 ujednoznacz

-0.56

 eletr

-0.55

itology

-0.55

ValueMap

-0.55

POSITIVE LOGITS

 Serve

1.31

 serve

1.29

Serve

1.24

 serving

1.24

serve

1.17

 served

1.14

Serving

1.09

 Serving

1.07

 serves

1.05

serving

1.03

Activations Density 0.150%

cooking instructions or methods

serving food

prepared to serve

No Comments

No Known Activations