INDEX

Explanations

programming-related syntax and structure

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

abestanden

-0.59

Personensuche

-0.55

出版年

-0.53

 سكانية

-0.52

IntoConstraints

-0.52

 iconLine

-0.52

tagHelper

-0.52

 Exacts

-0.52

RSpec

-0.50

SequentialGroup

-0.49

POSITIVE LOGITS

最快更新

0.63

 professionisti

0.62

حف

0.61

 AssemblyTitle

0.61

 كومونز

0.60

prefixer

0.60

 gustaba

0.60

 Seeder

0.59

Datuak

0.59

AutoScale

0.58

Activations Density 0.189%

programming-related syntax and structure

No Comments

No Known Activations