INDEX

Explanations

performance rankings and positions in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 testSet

-0.58

ส่วน

-0.57

modi

-0.56

sopp

-0.56

TestBed

-0.55

ביוגרפיה

-0.55

 Dublin

-0.55

ophiles

-0.53

 awakeFromNib

-0.52

ubung

-0.52

POSITIVE LOGITS

 automatiques

0.59

VersionUID

0.59

 kasarigan

0.58

 ranking

0.57

 rankings

0.56

 posição

0.55

enterOuterAlt

0.55

 posisi

0.54

 dieux

0.54

 ranked

0.54

Activations Density 0.139%

performance rankings and positions in competitive contexts

No Comments

No Known Activations