INDEX

Explanations

terms related to extending or extrapolating information, particularly in theoretical contexts

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

脚注の使い方

-0.48

GORITH

-0.46

QMetaType

-0.44

HttpStatus

-0.41

bindingNavigator

-0.41

MemoryWarning

-0.40

GOTREF

-0.39

$'

-0.38

 onPage

-0.38

ագրություններ

-0.38

POSITIVE LOGITS

 extend

1.13

 Extend

1.11

Extend

1.05

 extender

1.02

extend

1.02

 Extended

0.99

Extended

0.96

 extended

0.96

 extension

0.95

extended

0.95

Activations Density 0.176%

terms related to extending or extrapolating information, particularly in theoretical contexts

No Comments

No Known Activations