INDEX

Explanations

terms related to machine learning concepts, particularly focused on unique class transformations and data structures in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 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

transQ

-0.68

 '\\;'

-0.64

 gynhyrchwyd

-0.63

UnusedPrivate

-0.63

RegressionTest

-0.54

AnchorTagHelper

-0.53

findpost

-0.52

 Reſ

-0.52

достатки

-0.52

NameInMap

-0.52

POSITIVE LOGITS

 &___

0.41

groupBy

0.34

 defaultdict

0.34

 setPassword

0.33

groupby

0.33

<!--

0.28

 patterns

0.28

MessageOf

0.28

SharedCtor

0.28

Activations Density 0.746%

terms related to machine learning concepts, particularly focused on unique class transformations and data structures in programming

No Comments

No Known Activations