INDEX

Explanations

quantitative data and statistical results in a scientific document

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

Comparing different intensities or amounts

np_acts-logits-general · gemini-2.0-flash

lists of numbers and items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

parsedMessage

-0.68

 Instead

-0.40

 Exactos

-0.39

exitRule

-0.39

StoryboardSegue

-0.37

Instead

-0.37

phrine

-0.35

batore

-0.35

 textStatus

-0.35

verifyException

-0.35

POSITIVE LOGITS

jsonwebtoken

0.64

 further

0.62

beyond

0.59

 beyond

0.59

further

0.59

webElementXpaths

0.57

 advanced

0.55

 deeper

0.54

 larger

0.53

 bigger

0.52

Activations Density 0.946%

quantitative data and statistical results in a scientific document

Comparing different intensities or amounts

lists of numbers and items

No Comments

No Known Activations