INDEX

Explanations

programming-related keywords and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

RUnlock

-0.72

urlpatterns

-0.64

IndentedString

-0.63

elemField

-0.62

Personendaten

-0.61

GEBURTSDATUM

-0.60

RegressionTest

-0.60

principalColumn

-0.58

HasOne

-0.58

EDEFAULT

-0.58

POSITIVE LOGITS

hassee

0.56

KommentareTeilen

0.55

 directions

0.48

nikova

0.47

 hens

0.47

})*/

0.46

igner

0.46

ENESS

0.45

ruly

0.45

belt

0.45

Activations Density 0.124%

programming-related keywords and functions

No Comments

No Known Activations