INDEX

Explanations

identifiers and numerical values in a structured format

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

specific numerical data or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

 tartalomajánló

-0.59

ineno

-0.58

appé

-0.54

ветить

-0.53

()])

-0.52

GIVEREF

-0.50

RegistryLite

-0.47

்கள்

-0.44

 güneş

-0.43

openSession

-0.42

POSITIVE LOGITS

 AssemblyTitle

0.66

KommentareTeilen

0.63

 PopupWindow

0.62

`,

0.61

TestingModule

0.61

psum

0.61

原始内容存档于

0.59

PyErr

0.58

 AssemblyCompany

0.58

ErrUnexpectedEOF

0.57

Activations Density 0.087%

identifiers and numerical values in a structured format

specific numerical data or identifiers

No Comments

No Known Activations