INDEX

Explanations

code structures related to function definitions and their properties

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

Dislikes

-0.63

MessageOf

-0.62

 يتيمه

-0.59

ArgsConstructor

-0.56

oredCriteria

-0.54

 SEDS

-0.54

]='\

-0.50

χα

-0.50

StackSize

-0.49

KEEP

-0.49

POSITIVE LOGITS

 function

1.83

function

1.73

 Function

1.27

 functions

1.23

def

1.20

 función

1.20

 fonction

1.20

函数

1.19

 funzione

1.18

 função

1.14

Activations Density 0.126%

code structures related to function definitions and their properties

No Comments

No Known Activations