INDEX

Explanations

statistical terms related to data analysis and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 GenerationType

-0.99

<bos>

-0.61

SharedCtor

-0.58

RegressionTest

-0.54

 demikian

-0.51

zköz

-0.50

IsContent

-0.50

 accordingly

-0.50

 bezeichneter

-0.49

NOTA

-0.48

POSITIVE LOGITS

Personendaten

0.72

CPtr

0.61

Geplaatst

0.58

 ITIS

0.56

 استنادى

0.55

twimg

0.54

ulic

0.53

guém

0.52

'},

0.52

bl

0.52

Activations Density 0.619%

statistical terms related to data analysis and formatting

No Comments

No Known Activations