INDEX

Explanations

punctuation marks used to separate items in a list

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ContentAsync

-0.94

SequentialGroup

-0.87

httphttps

-0.85

揄

-0.81

ValueStyle

-0.78

featureID

-0.76

 AttributeSet

-0.75

viewDidLoad

-0.74

 doGet

-0.73

DrawerToggle

-0.71

POSITIVE LOGITS

 başına

0.54

 знаешь

0.50

getSupport

0.49

 public

0.49

amb

0.49

 može

0.48

ساس

0.48

pel

0.48

public

0.48

Activations Density 0.050%

punctuation marks used to separate items in a list

No Comments

No Known Activations