INDEX

Explanations

technical terms and values related to character encoding and metadata configurations

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.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

 CreateTagHelper

-0.52

 betweenstory

-0.49

 whistled

-0.48

lore

-0.47

weightedMode

-0.46

 թվական

-0.46

utex

-0.44

 зо

-0.44

Fug

-0.43

ertes

-0.43

POSITIVE LOGITS

routeProvider

0.52

AccessorTable

0.47

PerformLayout

0.44

 detect

0.39

Външни

0.39

detect

0.39

municipi

0.38

➯

0.38

 Bewußt

0.38

 detects

0.37

Activations Density 0.021%

technical terms and values related to character encoding and metadata configurations

No Comments

No Known Activations