INDEX

Explanations

programming constructs and syntax elements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

مان

-0.52

 %@",

-0.45

Des

-0.41

sus

-0.39

<eos>

-0.39

‌

-0.39

%@

-0.39

()">

-0.39

des

-0.39

IZ

-0.39

POSITIVE LOGITS

 >=",

0.91

 ddelweddau

0.88

 myſelf

0.79

RegressionTest

0.79

RenderAtEndOf

0.79

featureID

0.78

ImageContext

0.78

AsUp

0.78

enumi

0.77

iNdEx

0.76

Activations Density 0.422%

programming constructs and syntax elements in code

No Comments

No Known Activations