INDEX

Explanations

syntax related to function definitions and calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 itſelf

-0.55

 fluidity

-0.51

onViewCreated

-0.50

 Theſe

-0.50

 staffs

-0.49

 useSelector

-0.48

ılığı

-0.48

EDF

-0.47

 utafitiHapana

-0.47

 fert

-0.47

POSITIVE LOGITS

setVerticalGroup

0.79

BeginContext

0.65

 forKey

0.65

AlterField

0.63

addCriterion

0.62

 EconPapers

0.62

FieldBuilder

0.61

awtextra

0.60

MessageTagHelper

0.60

/***/

0.58

Activations Density 0.013%

syntax related to function definitions and calls

No Comments

No Known Activations