INDEX

Explanations

terms and phrases related to coordinates

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

Skocz

-0.67

 Fein

-0.65

SharedDtor

-0.65

TestBed

-0.64

NewUrlParser

-0.63

ness

-0.63

ers

-0.63

 Bloomfield

-0.61

梅

-0.60

es

-0.60

POSITIVE LOGITS

 Coordinate

0.93

 coordinate

0.81

 Coordinates

0.80

 Contra

0.79

 مشين

0.78

 coordinates

0.77

cottage

0.77

coordinates

0.75

 COORDIN

0.74

Coordinates

0.74

Activations Density 0.155%

terms and phrases related to coordinates

No Comments

No Known Activations