INDEX

Explanations

phrases related to statistical analysis and methods

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

Follows "was" or "were" and precedes "used"

np_acts-logits-general · gemini-2.0-flash

was/were used or applied

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

Datuak

-0.86

الحياه

-0.70

 препратки

-0.70

 nakalista

-0.66

 kasarigan

-0.63

 متعلقه

-0.63

MLLoader

-0.63

 مواليد

-0.63

 незавершена

-0.62

èdia

-0.62

POSITIVE LOGITS

 used

3.31

used

2.73

 Used

2.66

Used

2.62

 USED

2.33

 utilized

2.09

 utilisé

1.98

 utilisés

1.92

 employed

1.92

 utilizado

1.91

Activations Density 1.213%

phrases related to statistical analysis and methods

Follows "was" or "were" and precedes "used"

was/were used or applied

No Comments

No Known Activations