INDEX

Explanations

references to patents and formal descriptions of technological methods

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

Followed by patents or models

np_acts-logits-general · gemini-2.0-flash

in a nutshell

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

StructEnd

-0.58

 HttpNotFound

-0.52

 саны

-0.51

%)$

-0.48

事も

-0.48

LayoutConstraint

-0.47

막

-0.46

CloseOperation

-0.46

 tampoco

-0.46

 fritas

-0.45

POSITIVE LOGITS

 Basically

0.95

Basically

0.90

 Essentially

0.87

Essentially

0.86

 суть

0.85

 polega

0.84

 basically

0.81

basically

0.81

 involves

0.80

volves

0.79

Activations Density 0.779%

references to patents and formal descriptions of technological methods

Followed by patents or models

in a nutshell

No Comments

No Known Activations