INDEX

Explanations

terms related to specific characters and series in fictional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-0.63

 kasarigan

-0.62

 Werden

-0.61

قایناق‌لار

-0.59

:✨

-0.59

 ProtoMessage

-0.58

msgTypes

-0.55

parsedMessage

-0.54

 родился

-0.54

MessageOf

-0.53

POSITIVE LOGITS

 NgModule

0.69

VersionUID

0.65

ècie

0.59

\{\\

0.57

 onAnimation

0.56

ymce

0.55

abcdefghijklmnop

0.54

haviors

0.53

ServiceTest

0.51

hoven

0.51

Activations Density 0.989%

terms related to specific characters and series in fictional contexts

No Comments

No Known Activations