INDEX

Explanations

technical terms related to data processing and manipulation

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

GeneratedCode

-0.70

Šaltiniai

-0.63

 myſelf

-0.62

ScopeManager

-0.60

 SwitchCompat

-0.60

CGRectMake

-0.59

CodeAttribute

-0.59

 judicia

-0.59

VersionUID

-0.59

KEYCODE

-0.58

POSITIVE LOGITS

fhir

0.63

 ddelweddau

0.63

 فريبيس

0.62

ributes

0.50

حياته

0.49

enddo

0.47

dcterms

0.46

ENDIF

0.45

بوابة

0.45

 grounding

0.44

Activations Density 0.735%

technical terms related to data processing and manipulation

No Comments

No Known Activations