INDEX

Explanations

references to alternatives or different options

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ագրություններ

-0.65

ⓧ

-0.62

 emphasise

-0.58

IconModule

-0.58

ANDUM

-0.58

PhysRev

-0.57

 HomeComponent

-0.56

pushFollow

-0.56

 Peel

-0.56

 quæ

-0.56

POSITIVE LOGITS

ViewFeatures

0.61

ftagPool

0.57

ItemBackground

0.54

}$.\\

0.53

parsedMessage

0.52

satunya

0.52

 Wikipedia

0.51

PreferredItem

0.51

зулта

0.51

Activations Density 0.144%

references to alternatives or different options

No Comments

No Known Activations