INDEX

Explanations

code-related syntax and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 autorytatywna

-0.86

SharedDtor

-0.73

DockStyle

-0.64

::_('

-0.64

 ویکی‌پدیا

-0.63

WriteBarrier

-0.62

GEBURTSDATUM

-0.61

Jereo

-0.60

RegressionTest

-0.59

setVerticalGroup

-0.58

POSITIVE LOGITS

 parseInt

1.33

parseInt

1.23

Integer

1.22

 Integer

1.17

 atoi

1.11

 integer

1.05

int

1.02

atoi

1.00

Int

1.00

int

0.99

Activations Density 0.207%

code-related syntax and function definitions

No Comments

No Known Activations