INDEX

Explanations

references to scientific studies or citations used within 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

 Италијани

-0.84

 تضيفلها

-0.82

 betweenstory

-0.81

webElement

-0.78

tagHelper

-0.76

 resourceCulture

-0.74

SBATCH

-0.73

"]=

-0.72

 propOrder

-0.72

 autorytatywna

-0.69

POSITIVE LOGITS

0.56

 gelegen

0.50

 schlägt

0.48

Demografia

0.47

 Kälte

0.45

cassert

0.45

 tevens

0.43

quinone

0.43

 quelquefois

0.42

یلی

0.41

Activations Density 0.202%

references to scientific studies or citations used within the text

No Comments

No Known Activations