INDEX

Explanations

references to application components and their functionalities in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

SourceChecksum

-0.82

}{*}{}

-0.71

'):

-0.69

`{.

-0.64

')):

-0.63

 utafitiHapana

-0.62

KZ

-0.61

;">

-0.61

});*/

-0.60

**

-0.60

POSITIVE LOGITS

 "..\..\..\

0.65

adaptiveStyles

0.61

 "..\..\

0.59

ngdoc

0.57

NOON

0.51

QApplication

0.51

guous

0.51

drück

0.50

almaz

0.50

 AppBundle

0.50

Activations Density 0.129%

references to application components and their functionalities in a coding context

No Comments

No Known Activations