INDEX

Explanations

lines of code and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 mostrarán

-0.49

Sure

-0.47

webElementGuid

-0.46

addPreferredGap

-0.45

PRNewswire

-0.45

koz

-0.44

WithTag

-0.43

WriteTagHelper

-0.42

acağına

-0.42

serde

-0.42

POSITIVE LOGITS

 tartalomajánló

0.99

 Roskov

0.81

 Paglinawan

0.80

 ویکی‌پدیا

0.79

</table>

0.78

 виправивши

0.77

UnsafeEnabled

0.75

पया

0.73

 MainAxisSize

0.73

örper

0.72

Activations Density 0.392%

lines of code and programming constructs

No Comments

No Known Activations