INDEX

Explanations

phrases related to comparisons and measurements of value or quality

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

Comparative adjectives

np_acts-logits-general · gemini-2.0-flash

comparative quantifiers and degree modifiers

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

tvguidetime

-0.47

nextProps

-0.40

nach

-0.40

Vorlage

-0.38

재

-0.38

chay

-0.38

 Whereas

-0.37

Whereas

-0.36

ULING

-0.36

ITAS

-0.36

POSITIVE LOGITS

RegistryLite

0.83

 disso

0.82

นั้น

0.79

帖最后由

0.74

worse

0.71

 worse

0.70

 useDispatch

0.68

 nisso

0.68

DoubleQuotes

0.68

 dépass

0.66

Activations Density 0.309%

phrases related to comparisons and measurements of value or quality

Comparative adjectives

comparative quantifiers and degree modifiers

No Comments

No Known Activations