INDEX

Explanations

error handling and response preparation in code

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

before unusual capitalization

np_acts-logits-general · gemini-2.0-flash

scientific and mathematical terms

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

INCREF

-0.56

Cyfeiriadau

-0.55

RegressionTest

-0.55

 AssemblyTitle

-0.53

 ModelExpression

-0.51

Демографія

-0.50

 fass

-0.48

 Verder

-0.47

ilik

-0.47

 Fright

-0.46

POSITIVE LOGITS

BagConstraints

0.70

expandindo

0.61

enumi

0.60

ISupport

0.57

ViewFeatures

0.55

 Мексичка

0.54

 مشين

0.53

inSlope

0.52

 مرئيه

0.52

 кӀош

0.51

Activations Density 0.224%

error handling and response preparation in code

before unusual capitalization

scientific and mathematical terms

No Comments

No Known Activations