INDEX

Explanations

phrases related to relationships and interactions within complex systems or data

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

meaning "any" or "anything."

np_acts-logits-general · gemini-2.0-flash

any error or affected

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

windowFixed

-0.62

AndGet

-0.55

psack

-0.55

Scénario

-0.52

الإنجليزية

-0.49

AsUp

-0.44

plin

-0.42

номи

-0.42

toMatch

-0.42

ErrorListener

-0.41

POSITIVE LOGITS

 quelconque

1.53

 anything

1.44

any

1.30

 anymore

1.25

nor

1.23

anything

1.19

 quelcon

1.08

 mitään

1.07

or

1.07

 apapun

1.06

Activations Density 1.393%

phrases related to relationships and interactions within complex systems or data

meaning "any" or "anything."

any error or affected

No Comments

No Known Activations