INDEX

Explanations

specific numerical or statistical data related to health or medication usage

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

ConstraintMaker

-0.60

orteur

-0.57

 مرئيه

-0.56

 hâte

-0.55

kloped

-0.54

pography

-0.54

ξη

-0.54

 thereof

-0.52

 prefixes

-0.52

símbolo

-0.51

POSITIVE LOGITS

 autorytatywna

0.67

IContainer

0.67

Хьажоргаш

0.64

 intptr

0.61

vací

0.58

idjan

0.57

jspb

0.57

esac

0.57

 <<<<<<<<<<<<<<

0.56

 Audiodateien

0.56

Activations Density 0.829%

specific numerical or statistical data related to health or medication usage

No Comments

No Known Activations