INDEX

Explanations

terms and syntax related to programming, especially regarding values and parameters in code

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

state of Delaware

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

AndEndTag

-0.58

 estekak

-0.55

AutoScale

-0.50

]")]

-0.48

CloseOperation

-0.48

脚注の使い方

-0.46

)))));

-0.44

)++;

-0.44

}],

-0.42

Notae

-0.42

POSITIVE LOGITS

InputBorder

0.49

󠁴

0.40

CWE

0.39

limit

0.39

 ilimit

0.39

 Spisak

0.39

 Vall

0.39

енча

0.38

 instead

0.38

AppMethodBeat

0.38

Activations Density 0.006%

terms and syntax related to programming, especially regarding values and parameters in code

state of Delaware

No Comments

No Known Activations