INDEX

Explanations

code-related terms and references to threading and synchronization mechanisms

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

ρίζ

-0.51

bray

-0.49

olingo

-0.44

fromCharCode

-0.42

loem

-0.42

 Sagittarius

-0.41

mendations

-0.41

 delegación

-0.41

verk

-0.41

 FILLER

-0.40

POSITIVE LOGITS

 lock

1.63

lock

1.58

 Lock

1.45

 locks

1.41

Lock

1.40

 LOCK

1.32

 locking

1.31

LOCK

1.31

locks

1.31

 mutex

1.26

Activations Density 0.389%

code-related terms and references to threading and synchronization mechanisms

No Comments

No Known Activations