INDEX

Explanations

references to "plane" and its variants in the context of spatial or geometrical descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Viitteet

-0.80

 russes

-0.76

 initComponents

-0.74

 cref

-0.73

 الحره

-0.63

EndContext

-0.61

+:+

-0.58

 flaws

-0.58

مصادر

-0.58

="?

-0.58

POSITIVE LOGITS

Position

0.96

plane

0.83

 Plane

0.78

Plane

0.77

 plane

0.74

 PLANE

0.70

 resourceCulture

0.69

PLANE

0.64

setPosition

0.63

 Position

0.62

Activations Density 0.093%

references to "plane" and its variants in the context of spatial or geometrical descriptions

No Comments

No Known Activations