INDEX

Explanations

terms related to weight and heaviness

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

Mentions weight or weighing

np_acts-logits-general · gemini-2.0-flash

how things weigh

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

InjectAttribute

-0.57

∮

-0.55

IContainer

-0.54

 Савезне

-0.52

AndEndTag

-0.51

mogorov

-0.51

bė

-0.49

pyplot

-0.47

ficos

-0.47

ʌ

-0.45

POSITIVE LOGITS

 weight

3.10

 weights

2.76

weight

2.74

 weigh

2.69

 Weight

2.60

Weight

2.59

 WEIGHT

2.56

 weighs

2.56

 weighing

2.51

 weighed

2.42

Activations Density 0.480%

terms related to weight and heaviness

Mentions weight or weighing

how things weigh

No Comments

No Known Activations