INDEX

Explanations

references to maps and locations

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

so

-0.47

下

-0.43

 learned

-0.42

reg

-0.42

ed

-0.42

oc

-0.42

-0.41

gridy

-0.41

POSITIVE LOGITS

 للاسماء

0.69

出版年

0.59

 étoit

0.57

 Houſe

0.57

tagHelperRunner

0.56

ViewImports

0.54

IntOverflow

0.52

 Perſ

0.51

 ModelExpression

0.50

Diweddarwch

0.50

Activations Density 0.009%

references to maps and locations

No Comments

No Known Activations