INDEX

Explanations

mentions of autogenerated methods and error handling in programming contexts

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

before "and" or ":" (often article metadata)

np_acts-logits-general · gemini-2.0-flash

article and approved materials

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Vidite

-0.62

Portale

-0.57

 nakalista

-0.57

żeli

-0.56

<bos>

-0.55

niana

-0.55

 brightest

-0.54

ørn

-0.54

 Roskov

-0.53

="@

-0.52

POSITIVE LOGITS

MemoryWarning

1.01

 OnInit

0.71

 contextLoads

0.67

WebVitals

0.64

complexContent

0.62

 TestBed

0.61

UseVisualStyle

0.61

 الرياضيه

0.60

parsedMessage

0.59

dafx

0.58

Activations Density 0.071%

mentions of autogenerated methods and error handling in programming contexts

before "and" or ":" (often article metadata)

article and approved materials

No Comments

No Known Activations