INDEX

Explanations

references to numerical data or legal statutes

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

Followed by a number

np_acts-logits-general · gemini-2.0-flash

citations or numbered lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ContentValues

-0.46

 eventName

-0.39

OGND

-0.39

IsContent

-0.37

WaitGroup

-0.35

 appId

-0.35

PyExc

-0.35

 memberId

-0.34

 QName

-0.34

Pozri

-0.33

POSITIVE LOGITS

 excerpts

1.66

 excerpt

1.65

 extracts

1.50

 extract

1.41

excerpt

1.29

 Extract

1.26

Excerpt

1.25

 Excerpt

1.25

 Extracts

1.21

extract

1.18

Activations Density 0.748%

references to numerical data or legal statutes

Followed by a number

citations or numbered lists

No Comments

No Known Activations