INDEX

Explanations

terms related to functioning and operations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PerformLayout

-0.64

 joining

-0.59

icksburg

-0.54

 gedaan

-0.53

celes

-0.51

 rushing

-0.50

 hurrying

-0.50

 siting

-0.49

addContainerGap

-0.49

djangoproject

-0.47

POSITIVE LOGITS

 parallel

0.78

 independently

0.74

 autonom

0.73

 smoothly

0.72

 ComVisible

0.72

 efficiently

0.72

Atsauces

0.69

ChildIndex

0.67

 الحره

0.66

 optimally

0.65

Activations Density 0.271%

terms related to functioning and operations in various contexts

No Comments

No Known Activations