INDEX

Explanations

elements related to greetings and polite interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/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.39.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

httphttps

-0.57

FormTagHelper

-0.47

 fritas

-0.43

ConstraintMaker

-0.42

HasAnnotation

-0.41

EndContext

-0.41

 besos

-0.41

lós

-0.41

期刊论文

-0.40

 sociala

-0.40

POSITIVE LOGITS

 shootings

0.45

 ontdek

0.44

 discovery

0.43

 bluff

0.41

 inso

0.40

 Venez

0.40

 chor

0.39

 asso

0.39

 Numer

0.38

xicity

0.36

Activations Density 0.354%

elements related to greetings and polite interactions

No Comments

No Known Activations