INDEX

Explanations

terms associated with security exceptions and permissions in programming context

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

Code or mathematical expressions

np_acts-logits-general · gemini-2.0-flash

.NET framework versions

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

blon

-0.56

HomeAsUpEnabled

-0.55

PyExc

-0.51

 Viitattu

-0.49



-0.49

ORAGE

-0.49

Tra

-0.48

ieteur

-0.46

RSpec

-0.45

bitur

-0.43

POSITIVE LOGITS

0.65

Clik

0.64

 AttributeSet

0.58

ampingi

0.56

orianCalendar

0.55

UnknownFieldSet

0.55

省市镇

0.53

 resourceCulture

0.52

jsii

0.51

lapsingToolbar

0.51

Activations Density 0.312%

terms associated with security exceptions and permissions in programming context

Code or mathematical expressions

.NET framework versions

No Comments

No Known Activations