INDEX

Explanations

keywords related to abilities and powers in a fictional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ModelExpression

-0.62

DeleteBehavior

-0.58

 awakeFromNib

-0.54

 ExecuteAsync

-0.54

 players

-0.53

orestation

-0.52

players

-0.51

ponses

-0.51

 Players

-0.50

TestingModule

-0.50

POSITIVE LOGITS

########.

0.58

 moves

0.55

 powers

0.51

 stat

0.51

 abilities

0.51

msgTypes

0.48

fillType

0.47

 spells

0.47

 pinulongan

0.46

 attacks

0.46

Activations Density 0.413%

keywords related to abilities and powers in a fictional context

No Comments

No Known Activations

keywords related to abilities and powers in a fictional context

No Comments

No Known Activations