INDEX

Explanations

references to data, classifications, and formal systems in a structured context

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IRQn

-0.41

istoitu

-0.40

eqn

-0.36

Garantía

-0.35

+:+

-0.34

ợn

-0.34

차

-0.34

essoa

-0.34

 electrolux

-0.33

})));

-0.33

POSITIVE LOGITS

 مشين

0.59

 تانيه

0.57

 createSprite

0.57

 snippetHide

0.55

󠁣

0.53

SequentialGroup

0.52

 iprot

0.47

bzero

0.46

writerow

0.46

 مرئيه

0.46

Activations Density 0.248%

references to data, classifications, and formal systems in a structured context

No Comments

No Known Activations