INDEX

Explanations

terms related to user interactions and commands within a chat or messaging platform

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Filmografie

-0.68

__':

-0.63

__":

-0.57

awtextra

-0.56

EOUT

-0.56

URIComponent

-0.55

✨:

-0.55

ChildScrollView

-0.55

NewUrlParser

-0.54

levering

-0.53

POSITIVE LOGITS

discord

0.56

 Discord

0.56

๖

0.56

bukkit

0.54

ق

0.54

 mergeFrom

0.53

 giovan

0.52

 Référence

0.52

 clarification

0.51

حوالہ

0.50

Activations Density 0.099%

terms related to user interactions and commands within a chat or messaging platform

No Comments

No Known Activations