INDEX

Explanations

terms related to asymptotic equivalence in statistical contexts

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

Tends to a limit

np_acts-logits-general · gemini-2.0-flash

tends to limit

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

expandindo

-0.70

 незавершена

-0.59

$_['

-0.52

 հղումներ

-0.51

RenderAtEndOf

-0.49

 duele

-0.49

sidemargin

-0.48

mtrl

-0.48

 Aquila

-0.48

 depred

-0.47

POSITIVE LOGITS

 limit

1.52

lim

1.35

 Limit

1.33

lim

1.32

Limit

1.27

limit

1.26

 limits

1.21

 LIMIT

1.18

 limite

1.17

 limiting

1.14

Activations Density 1.205%

terms related to asymptotic equivalence in statistical contexts

Tends to a limit

tends to limit

No Comments

No Known Activations

terms related to asymptotic equivalence in statistical contexts

Tends to a limit

tends to limit

No Comments

No Known Activations