INDEX

Explanations

mentions of time periods and roles within hierarchies or organizations

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

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

 ASAP

-0.59

msgSender

-0.59

Weblinks

-0.59

SequentialGroup

-0.58

PhysRevD

-0.57

ropa

-0.52

QFont

-0.52

حياته

-0.51

chromedriver

-0.51

 proceed

-0.50

POSITIVE LOGITS

期间

0.84

每一次

0.77

 countless

0.77

 culminating

0.72

 aikana

0.69

 culminated

0.67

 tantôt

0.66

 innumerable

0.65

 During

0.65

during

0.65

Activations Density 0.367%

mentions of time periods and roles within hierarchies or organizations

No Comments

No Known Activations