INDEX

Explanations

references to Oracle and its features or related concepts

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

Japanese honorifics or polite prefixes

np_acts-logits-general · gemini-2.0-flash

`su` followed by `es` or `face`, `ace` followed by `tabular` or `tracking`, `ご` followed by `不在`, `お` followed by `とな`

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Baillargeon

-0.58

ContentAsync

-0.53

 vôtre

-0.52

[]:

-0.52

actionMode

-0.51

 Audiodateien

-0.50

writerow

-0.50

rss

-0.49

 Konkur

-0.49

tonsoft

-0.49

POSITIVE LOGITS

:✨

0.76

apimachinery

0.65

 MainAxisSize

0.62

Espèce

0.59

XmlEnum

0.57

UpInside

0.56

IPAC

0.55

 intptr

0.55

نامه

0.54

InputBorder

0.52

Activations Density 0.091%

references to Oracle and its features or related concepts

Japanese honorifics or polite prefixes

`su` followed by `es` or `face`, `ace` followed by `tabular` or `tracking`, `ご` followed by `不在`, `お` followed by `とな`

No Comments

No Known Activations