INDEX

Explanations

references to incidents or events related to significant occurrences

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

references to incidents, particularly in a healthcare or regulatory context

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

incident reporting, precipitation, light, particle, cardiovascular

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

}{*}{

-0.62

MetaType

-0.60

CURLOPT

-0.54

PU

-0.53

 Tavares

-0.53

fillType

-0.53

wack

-0.53

weetened

-0.52

цездатний

-0.52

ništvo

-0.52

POSITIVE LOGITS

 متعلقه

1.03

 Incidents

0.92

ality

0.91

ally

0.89

 incidents

0.87

uality

0.87

alities

0.74

 itſelf

0.71

Occurred

0.71

als

0.69

Activations Density 0.024%

references to incidents or events related to significant occurrences

references to incidents, particularly in a healthcare or regulatory context

incident reporting, precipitation, light, particle, cardiovascular

No Comments

No Known Activations