INDEX

Explanations

addresses and location information

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

Appears before numbers

np_acts-logits-general · gemini-2.0-flash

address or phone number

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

mybatisplus

-0.71

bootstrapcdn

-0.67

PyExc

-0.65

FieldBuilder

-0.57

tagHelperRunner

-0.56

 BoxFit

-0.54

RRect

-0.53

OrWhiteSpace

-0.53

 amour

-0.52

 BufferedWriter

-0.51

POSITIVE LOGITS

:✨

0.58

 phone

0.56

Tel

0.56

TagHelpers

0.55

 Phone

0.54

Phone

0.54

DebuggerNonUser

0.52

 telt

0.52

ScopeManager

0.52

Tel

0.50

Activations Density 0.086%

addresses and location information

Appears before numbers

address or phone number

No Comments

No Known Activations