INDEX

Explanations

code-related errors and warnings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

__':

-0.59

таратура

-0.54

TintMode

-0.52

ValueGeneration

-0.52

tät

-0.51

 Flasche

-0.51

__':

-0.49

IonicModule

-0.49

yors

-0.49

zboi

-0.49

POSITIVE LOGITS

php

0.95

PHP

0.89

php

0.84

PHP

0.78

Php

0.73

BASEPATH

0.67

 Mysql

0.66

 MySQL

0.64

omla

0.64

 Biochem

0.63

Activations Density 0.377%

code-related errors and warnings

No Comments

No Known Activations