INDEX

Explanations

structured or systematic frameworks and guidelines related to various topics

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

ThroughAttribute

-0.63

ChildScrollView

-0.57

Personensuche

-0.57

parsedMessage

-0.56

EndContext

-0.56

MemoryWarning

-0.56

ValueStyle

-0.56

webElementXpaths

-0.54

 незавершена

-0.54

ivir

-0.53

POSITIVE LOGITS

 structured

0.52

 orderly

0.49

 planned

0.48

 formal

0.47

 固定

0.47

 regularity

0.46

 plan

0.45

 precision

0.45

 structure

0.44

 standardi

0.41

Activations Density 0.601%

structured or systematic frameworks and guidelines related to various topics

No Comments

No Known Activations