INDEX

Explanations

references to medical guidelines and recommendations

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

Mentions guidelines or recommendations

np_acts-logits-general · gemini-2.0-flash

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

WaitGroup

-0.32

 Kearns

-0.30

TagMode

-0.29

AnchorStyles

-0.29

prepareStatement

-0.27

 gynhyrchwyd

-0.27

 ModelExpression

-0.26

__':

-0.25

 gambe

-0.25

 كومونز

-0.24

POSITIVE LOGITS

 guidelines

2.11

 Guidelines

1.81

guidelines

1.73

Guidelines

1.71

 guideline

1.66

 GUIDELINES

1.50

 Guideline

1.46

 recommendations

1.38

 standards

1.35

 guidance

1.34

Activations Density 0.637%

references to medical guidelines and recommendations

Mentions guidelines or recommendations

No Comments

No Known Activations