INDEX

Explanations

instances of list or itemization formatting in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

contentLoaded

-0.83

afficheront

-0.64

 Вікі

-0.64

 propOrder

-0.64

 doInBackground

-0.63

 sclero

-0.61

GeoNames

-0.59

BagLayout

-0.59

Czytaj

-0.59

autoload

-0.58

POSITIVE LOGITS

//

1.02

itemize

0.94

">-

0.90

 }^{*}$

0.89

€¢

0.88

0.86

:*

0.83

">*

0.82

-*

0.81

0.79

Activations Density 0.019%

instances of list or itemization formatting in the text

No Comments

No Known Activations