INDEX

Explanations

function definitions and their return statements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.89

 onAnimation

-0.84

\{\\

-0.68

 يتيمه

-0.65

Nazionale

-0.65

 Italijani

-0.62

Espèce

-0.61

igshid

-0.61

躇

-0.61

šķ

-0.61

POSITIVE LOGITS

 ISNI

0.73

fromCharCode

0.56

InvalidProtocol

0.54

 parseFrom

0.53

SerializedSize

0.53

 PublicKey

0.53

Autoritní

0.49

 שלה

0.48

RAINT

0.47

execSQL

0.46

Activations Density 0.107%

function definitions and their return statements

No Comments

No Known Activations