INDEX

Explanations

instances of the word "see" and its variants

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

"see" followed by an article

np_acts-logits-general · gemini-2.0-flash

seeing and variations

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

 թվական

-0.69

 bezeichneter

-0.66

Ārējās

-0.64

ografija

-0.63

@"/

-0.63

Poloha

-0.63

 Mainland

-0.62

További

-0.62

 Marek

-0.61

انيف

-0.61

POSITIVE LOGITS

 Sees

1.30

 sees

1.23

see

1.15

SEE

1.13

See

1.12

see

1.11

See

1.06

Saw

1.06

saw

1.06

sees

1.05

Activations Density 0.151%

instances of the word "see" and its variants

"see" followed by an article

seeing and variations

No Comments

No Known Activations