INDEX

Explanations

references to conflict or battles involving good versus evil

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

ьаж

-0.56

findpost

-0.47

#+#

-0.46

 uska

-0.42

CultureInfo

-0.41

gdx

-0.40

UseVisualStyle

-0.40

 murmur

-0.39

 jury

-0.39

 reviewed

-0.38

POSITIVE LOGITS

 enemy

0.83

MemoryWarning

0.82

Демографія

0.81

 Roskov

0.80

 Enemy

0.73

makeConstraints

0.73

 enemies

0.72

 виправивши

0.71

ActionCreators

0.70

Enemy

0.68

Activations Density 0.458%

references to conflict or battles involving good versus evil

No Comments

No Known Activations