INDEX

Explanations

specific syntax or variable patterns typically found in programming or data structures

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

Hexadecimal byte representations

np_acts-logits-general · gemini-2.0-flash

hexadecimal numbers and dates

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

 שוליים

-0.52

InitVars

-0.52

="#"><

-0.49

PhysRev

-0.48

 gärna

-0.47

 التجار

-0.47

نتاج

-0.47

 next

-0.46

روان

-0.45

ellees

-0.44

POSITIVE LOGITS

 مرئيه

0.69



0.64

 كومونز

0.63

دانشنامهٔ

0.63

醐

0.62

Personensuche

0.60

 getItemId

0.59

UnsafeEnabled

0.59

enumi

0.58

XmlAccessType

0.57

Activations Density 0.297%

specific syntax or variable patterns typically found in programming or data structures

Hexadecimal byte representations

hexadecimal numbers and dates

No Comments

No Known Activations