INDEX

Explanations

mentions of specific names or terms related to individuals or entities, particularly those prefixed with 'Y'

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

Token "Y" followed by another character

np_acts-logits-general · gemini-2.0-flash

Y letter as a prefix or part of abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

verwijspagina

-0.82

 ویکی‌پدیا

-0.70

UnsafeEnabled

-0.61

intios

-0.60

rehension

-0.59

 bevis

-0.55

 pinulongan

-0.55

fael

-0.54

DotNetBar

-0.52

wek

-0.52

POSITIVE LOGITS

terday

0.80

揄

0.69

YC

0.68

 ymin

0.66

 ớt

0.65

 getY

0.63

Yol

0.63

Yel

0.62

 препратки

0.61

YP

0.60

Activations Density 0.294%

mentions of specific names or terms related to individuals or entities, particularly those prefixed with 'Y'

Token "Y" followed by another character

Y letter as a prefix or part of abbreviations

No Comments

No Known Activations