INDEX

Explanations

terms related to masks and disguises in relation to characters

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 كومونز

-0.59

 NavController

-0.50

findpost

-0.50

asymp

-0.49

Wiring

-0.49

ChildScrollView

-0.47

httphttps

-0.47

magnetism

-0.47

 المع

-0.46

providedIn

-0.46

POSITIVE LOGITS

 anonymity

0.85

 masks

0.85

 mask

0.81

 masked

0.81

 anonymous

0.66

 anonymously

0.66

 máscara

0.65

mask

0.64

masked

0.64

 anonim

0.61

Activations Density 0.018%

terms related to masks and disguises in relation to characters

No Comments

No Known Activations