INDEX

Explanations

terms related to vehicle safety and collision scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

/\.

-0.52

weightedMode

-0.52

 ligiloj

-0.49

 Италијани

-0.47

ftagPool

-0.47

 للمعارف

-0.47

horabuena

-0.47

Спасылкі

-0.46

evos

-0.45

AddHtmlAttribute

-0.44

POSITIVE LOGITS

 collision

0.50

reactstrap

0.48

 collisions

0.47

collision

0.43

 colliding

0.43

 Collision

0.42

 avoidance

0.41

衝突

0.41

WriteLiteral

0.40

 defense

0.39

Activations Density 0.260%

terms related to vehicle safety and collision scenarios

No Comments

No Known Activations