INDEX

Explanations

positive evaluations and descriptions of movies, concepts, and articles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dieux

-0.49

 tachy

-0.48

 soyez

-0.47

 valmist

-0.47

 visst

-0.46

vs

-0.46

 maggiori

-0.45

Certain

-0.45

 certain

-0.45

mw

-0.44

POSITIVE LOGITS

 BoxDecoration

0.78

pushFollow

0.75

ngdoc

0.73

mybatisplus

0.72

 wonderful

0.70

 referrerpolicy

0.70

fjspx

0.68

Numerade

0.67

wonderful

0.66

enumii

0.66

Activations Density 0.410%

positive evaluations and descriptions of movies, concepts, and articles

No Comments

No Known Activations