INDEX

Explanations

references to character deaths and their consequences in video games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ropical

-0.57

prechung

-0.55

 Drucker

-0.54

NOPQRST

-0.51

 hương

-0.51

 compete

-0.50

BorderSize

-0.50

MLLoader

-0.49

utzer

-0.49

neurs

-0.49

POSITIVE LOGITS

BeginInit

0.64

ukone

0.60

 незавершена

0.57

Rujuakan

0.56

 Normdatei

0.54

 TextAppearance

0.53

0.52

ButtonStyle

0.51

DLC

0.51

 يتيمه

0.51

Activations Density 0.101%

references to character deaths and their consequences in video games

No Comments

No Known Activations