INDEX

Explanations

terms and classes related to programming frameworks and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

FieldBuilder

-0.48

DeleteBehavior

-0.47

InSection

-0.45

Faker

-0.44

ού

-0.44

lichter

-0.43

coder

-0.42

дото

-0.42

BASELINE

-0.42

 kế

-0.42

POSITIVE LOGITS

Autoritní

0.72

Hentet

0.63

PFS

0.63

 cdti

0.63

 reaſon

0.62

 betweenstory

0.62

 يتيمه

0.61

 crdi

0.60

matically

0.59

DispatchToProps

0.58

Activations Density 0.635%

terms and classes related to programming frameworks and libraries

No Comments

No Known Activations