INDEX

Explanations

terms related to research studies and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 GenerationType

-0.60

findpost

-0.57

 Roskov

-0.54

Rujuakan

-0.53

MethodManager

-0.52

SpringBootTest

-0.50

 NSCoder

-0.50

ChildScrollView

-0.49

 typelib

-0.49

Diwedd

-0.47

POSITIVE LOGITS

 <=",

0.52

 AppCompatTheme

0.45

ArrowToggle

0.44

IntoConstraints

0.42

SharedCtor

0.42

rungsseite

0.41

ViewInit

0.40

 otomatig

0.38

 autorytatywna

0.37

 OMITBAD

0.37

Activations Density 2.244%

terms related to research studies and findings

No Comments

No Known Activations