INDEX

Explanations

identifiers and their associated values in a structured format

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

id, path, record, address

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

balleur

-0.55

AndEndTag

-0.52

 TextInputType

-0.51

readFileSync

-0.50

 invokingState

-0.49

énario

-0.48

المناصب

-0.46

oleic

-0.46

 fubject

-0.45

 HasFactory

-0.43

POSITIVE LOGITS

mybatisplus

0.41

horizontalLayout

0.41

AppMethodBeat

0.37

:')

0.37

istoitu

0.36

 ActivatedRoute

0.36

舺

0.35

kháu

0.34

 Reid

0.33

NotExist

0.32

Activations Density 0.096%

identifiers and their associated values in a structured format

id, path, record, address

No Comments

No Known Activations