INDEX

Explanations

references to figures and tables within the document

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

 الرياضيه

-0.98

+#+

-0.79

 فريبيس

-0.72

 lenker

-0.69

LookAnd

-0.67

ConstraintMaker

-0.64

Rohy

-0.61

 Administrativna

-0.61

 AssemblyCompany

-0.61

XmlAccessType

-0.60

POSITIVE LOGITS

 summarised

0.61

 detailed

0.59

 illustrated

0.58

detailed

0.54

 below

0.53

 captured

0.52

webElement

0.51

illustrated

0.51

 summarized

0.50

 herein

0.49

Activations Density 0.802%

references to figures and tables within the document

No Comments

No Known Activations