INDEX

Explanations

dates and numerical values associated with events or records

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

Years or date ranges

np_acts-logits-general · gemini-2.0-flash

years and dates

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

Kanpo

-0.49

bridal

-0.47

PyErr

-0.46

مزید

-0.46

 aceptas

-0.45

liminary

-0.45

 Salta

-0.45

ář

-0.44

ัติ

-0.44

ละคร

-0.44

POSITIVE LOGITS

MemoryWarning

0.74

parsedMessage

0.72

providedIn

0.69

GraphicsUnit

0.65

URLException

0.65

esModule

0.64

 فريبيس

0.63

invokeLater

0.63

WithIOException

0.59

Personensuche

0.58

Activations Density 0.057%

dates and numerical values associated with events or records

Years or date ranges

years and dates

No Comments

No Known Activations