INDEX

Explanations

references to miniaturized products or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

upuncture

-0.67

 ActionListener

-0.66

 useState

-0.65

JspWriter

-0.64

databind

-0.63

apunov

-0.61

DispatchToProps

-0.59

JsonProperty

-0.57

AssignableFrom

-0.55

 lumineuse

-0.55

POSITIVE LOGITS

Mini

2.91

 mini

2.90

 Mini

2.89

mini

2.67

 MINI

2.65

MINI

2.52

 miniature

2.14

 Minis

1.94

 Miniature

1.91

 minis

1.90

Activations Density 0.067%

references to miniaturized products or concepts

No Comments

No Known Activations