INDEX

Explanations

block comments and method definitions 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

ValueStyle

-0.76

webElementXpaths

-0.67

 Савезне

-0.65

oredCriteria

-0.65

RepeatedField

-0.64

CPtr

-0.63

COUVER

-0.63

ERVIS

-0.61

blessed

-0.59

Välislingid

-0.58

POSITIVE LOGITS

/**

0.76

 MainAxisSize

0.73

/**

0.72

".

0.68

RTA

0.68

"""

0.66

}*/

0.65

uxxxx

0.65

).

0.65

//}

0.63

Activations Density 0.018%

block comments and method definitions in code

No Comments

No Known Activations