INDEX

Explanations

titles and forms of nobility

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

following the title "Lord"

np_acts-logits-general · gemini-2.0-flash

lord and associated names or titles

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

脚注の使い方

-0.66

expandindo

-0.56

>{@

-0.56

vora

-0.53

oxone

-0.52

 Exacts

-0.52

Quelle

-0.51

])));

-0.50

ixon

-0.50

nodoc

-0.50

POSITIVE LOGITS

 Lords

0.89

 lords

0.75

AndEndTag

0.70

 lenker

0.64

 lord

0.64

Jeografia

0.62

 Lord

0.62

 LORD

0.61

LORD

0.60

حيط

0.58

Activations Density 0.059%

titles and forms of nobility

following the title "Lord"

lord and associated names or titles

No Comments

No Known Activations