INDEX

Explanations

programming-related terms and concepts, particularly those related to language translation and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

PrototypeOf

-0.66

 jarang

-0.55

 smtplib

-0.53

 didReceive

-0.51

calipsis

-0.51

 Galbraith

-0.50

 localVar

-0.50

 TextAppearance

-0.50

 pháp

-0.48

ictwo

-0.47

POSITIVE LOGITS

verifyException

0.66

Personendaten

0.65

 paff

0.64

 houſe

0.63

مصادر

0.63

 فريبيس

0.62

 purpoſe

0.61

 Houſe

0.60

—

0.60

ReusableCell

0.59

Activations Density 1.990%

programming-related terms and concepts, particularly those related to language translation and data handling

No Comments

No Known Activations