INDEX

Explanations

structure or framework in programming or data representation

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

</strong>

-0.75

تقاوى

-0.65

AutoScaleMode

-0.62

 CanadaChoose

-0.60

 CURIAM

-0.58

Scénario

-0.58

ริง

-0.57

$$

-0.56

DeleteBehavior

-0.56

viewDidLoad

-0.55

POSITIVE LOGITS

Personensuche

0.89

EditorBrowsable

0.67

setVerticalGroup

0.63

 Smarty

0.62

 createSlice

0.60

adaptiveStyles

0.58

isContained

0.56

URLException

0.56

Rhestr

0.54

 unknownFields

0.54

Activations Density 0.007%

structure or framework in programming or data representation

No Comments

No Known Activations