INDEX

Explanations

numerical references related to data or research findings

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

Numbers within text

np_acts-logits-general · gemini-2.0-flash

numbers, citations, and mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

fromnode

-0.71

 AssemblyCompany

-0.69

RTLD

-0.67

 referenties

-0.66

 متعلقه

-0.66

webElement

-0.63

TypedDataSet

-0.62

PhysRevD

-0.62

tagHelperRunner

-0.60

OGND

-0.60

POSITIVE LOGITS

SCL

0.52

simile

0.46

RST

0.45

ázka

0.44

SVC

0.44

Nye

0.43

Nye

0.43

phosa

0.42

opel

0.42

endpush

0.41

Activations Density 0.668%

numerical references related to data or research findings

Numbers within text

numbers, citations, and mathematical expressions

No Comments

No Known Activations