INDEX

Explanations

references to code structure and definitions

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.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

 بيها

-0.85

AndroidJUnit

-0.79

 HasFactory

-0.78

 noDo

-0.75

 Lightboxes

-0.71

InitVars

-0.70

 tartalomajánló

-0.69

PutMapping

-0.68

SerializedSize

-0.68

 <>",

-0.67

POSITIVE LOGITS

FlatAppearance

0.62

 LEAD

0.53

ISupport

0.50

atement

0.49

 Lead

0.49

stmt

0.49

shou

0.48

 Natale

0.48

 lead

0.47

θε

0.47

Activations Density 0.005%

references to code structure and definitions

No Comments

No Known Activations