INDEX

Explanations

numerical data and statistics related to test results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

BeginContext

-0.80

GEBURTSDATUM

-0.65

MLLoader

-0.64

abestanden

-0.64

RenderAtEndOf

-0.64

出版年

-0.63

principalTable

-0.63

ScopeManager

-0.60

 doInBackground

-0.56

Chham

-0.53

POSITIVE LOGITS

aksi

0.52

werth

0.48

onné

0.47

°

0.46

 precise

0.46

原始内容存档于

0.46

 MMMM

0.46

 tolerably

0.45

Citiți

0.45

jsxFileName

0.44

Activations Density 0.204%

numerical data and statistics related to test results

No Comments

No Known Activations