INDEX

Explanations

terms related to form and structure in various contexts

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

"Form" followed by various suffixes

np_acts-logits-general · gemini-2.0-flash

form and its derivations

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

########.

-0.56

ItemBackground

-0.55

TRIBUN

-0.53

MENAFN

-0.51

-0.50

 متعلقه

-0.49

ollectionView

-0.49

 MemoryStream

-0.48

litis

-0.48

dorp

-0.47

POSITIVE LOGITS

ulates

0.94

ulir

0.93

idable

0.93

alised

0.85

ulated

0.84

ulate

0.82

ulating

0.80

ulators

0.77

ulations

0.76

ulary

0.75

Activations Density 0.166%

terms related to form and structure in various contexts

"Form" followed by various suffixes

form and its derivations

No Comments

No Known Activations