INDEX

Explanations

references to authority figures and hierarchical structures in a narrative context

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

 AssemblyCulture

-0.66

 NavController

-0.56

 RouterModule

-0.53

/**

-0.52

ModelSerializer

-0.51

matchCondition

-0.51

XmlAccessType

-0.47

 ſever

-0.47

✨:

-0.47

tagext

-0.47

POSITIVE LOGITS

 tryna

0.39

back

0.38

 gotta

0.37

dam

0.36

 Flach

0.36

 acostumb

0.35

 hitter

0.34

xion

0.34

Nobody

0.34

 like

0.33

Activations Density 0.077%

references to authority figures and hierarchical structures in a narrative context

No Comments

No Known Activations