INDEX

Explanations

keywords and elements related to technical specifications or programming concepts

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

preceding "VPN", "matter", "summary", "abstract", or "more"

np_acts-logits-general · gemini-2.0-flash

summary, however, more, abstract, subject

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

 Wiktionnaire

-0.69

orited

-0.62

 Hemisphere

-0.61

σθαι

-0.61

ighed

-0.60

lapping

-0.60

inafter

-0.59

 HttpNotFound

-0.57

ticed

-0.56

vaders

-0.55

POSITIVE LOGITS

etheless

0.89

parsedMessage

0.84

éfono

0.75

resizingMask

0.74

oltre

0.72

rrggbb

0.72

aimana

0.68

tagext

0.67

inflater

0.66

клопе

0.66

Activations Density 2.634%

keywords and elements related to technical specifications or programming concepts

preceding "VPN", "matter", "summary", "abstract", or "more"

summary, however, more, abstract, subject

No Comments

No Known Activations