INDEX

Explanations

technical terms related to processes, configurations, and objects in a system

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

 BoxFit

-0.95

 initComponents

-0.91

CloseOperation

-0.86

بوابة

-0.82

المراجع

-0.81

 CreateTagHelper

-0.81

ſelves

-0.80

GEBURTS

-0.79

تقاوى

-0.78

Искәрмәләр

-0.76

POSITIVE LOGITS

the

0.71

 your

0.55

 them

0.55

0.53

らせ

0.52

ded

0.48

ed

0.48

 את

0.48

en

0.48

</i>

0.47

Activations Density 0.425%

technical terms related to processes, configurations, and objects in a system

No Comments

No Known Activations