INDEX

Explanations

specific scientific terms, particularly those related to hierarchical models and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 الحره

-0.56

ConstraintMaker

-0.54

 مرئيه

-0.53

psack

-0.53

jaciół

-0.51

 calendriers

-0.51

strates

-0.49

RectangleBorder

-0.48

 initComponents

-0.48

 lời

-0.47

POSITIVE LOGITS

rungsseite

0.73

 pinulongan

0.62

 appunto

0.61

 suspensão

0.53

oredCriteria

0.53

sizeCache

0.53

 ostavi

0.52

ThemeOverlay

0.51

OrBuilder

0.51

 dataSnapshot

0.51

Activations Density 0.644%

specific scientific terms, particularly those related to hierarchical models and statistics

No Comments

No Known Activations