INDEX

Explanations

insightful discussions and mentions of Hodge structures or related scientific concepts

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

Capitalized words followed by prepositions

np_acts-logits-general · gemini-2.0-flash

insight into / Hodge numbers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

parsedMessage

-1.15

 Савезне

-0.88

astify

-0.88

 ſind

-0.87

 Rosso

-0.87

ValueStyle

-0.87

 Majefty

-0.86

SerializedSize

-0.85

 MatDialog

-0.84

AccessorTable

-0.83

POSITIVE LOGITS

ness

0.62

Bos

0.61

fulness

0.59

Wad

0.56

Bos

0.56

 Grant

0.53

NESS

0.53

kh

0.51

ment

0.51

Activations Density 0.496%

insightful discussions and mentions of Hodge structures or related scientific concepts

Capitalized words followed by prepositions

insight into / Hodge numbers

No Comments

No Known Activations