INDEX

Explanations

code comments and documentation-related annotations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:✨

-0.95

 ivelany

-0.88

tagHelperRunner

-0.85

LookAnd

-0.84

SharedDtor

-0.83

Šaltiniai

-0.79

GEBURTSDATUM

-0.78

parsedMessage

-0.75

featureID

-0.75

IndentedString

-0.75

POSITIVE LOGITS

↵↵

0.80

<h2>

0.60

↵

0.59

<tr>

0.58

<h3>

0.56

<eos>

0.56

↵↵↵

0.50

↵↵↵↵

0.49

</table>

0.49

////////////////

0.48

Activations Density 0.072%

code comments and documentation-related annotations

No Comments

No Known Activations