INDEX

Explanations

content related to scientific research and data analysis metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AccessorTable

-0.55

^(@)

-0.52

:"-"`

-0.50

Citiți

-0.47

@",

-0.45

itol

-0.45

BagLayout

-0.45

allax

-0.44

 Sante

-0.43

Vivian

-0.43

POSITIVE LOGITS

NameInMap

0.69

IVEREF

0.62

gdx

0.61

 otomatig

0.60

Composable

0.60

SuppressLint

0.58

 uska

0.58

Portály

0.57

 مفص

0.56

typeparam

0.54

Activations Density 0.083%

content related to scientific research and data analysis metrics

No Comments

No Known Activations