INDEX

Explanations

terms related to education and learning tools

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

 surla

-0.62

 ModelExpression

-0.55

 calendriers

-0.55

 recommandée

-0.53

AntiForgeryToken

-0.52

 onPostExecute

-0.48

MergeFrom

-0.47

RenderAtEndOf

-0.47

밌

-0.46

 poveznice

-0.46

POSITIVE LOGITS

 Мексичка

1.16

ⓧ

0.72

 تضيفلها

0.65

 ComVisible

0.64

BeginContext

0.58

ChromeDriver

0.57

 Савезне

0.57

省市镇

0.56

LookAnd

0.54

Gön

0.53

Activations Density 36.441%

terms related to education and learning tools

No Comments

No Known Activations