INDEX

Explanations

references to distances, specifically in kilometers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

myspace

-0.56

ustin

-0.53

 Holly

-0.52

性

-0.51

之助

-0.51

ので

-0.50

Holly

-0.50

getSingle

-0.50

Domaine

-0.50

[&

-0.50

POSITIVE LOGITS

km

2.91

km

2.65

 kilometres

2.06

kms

2.05

 kilometers

2.03

 км

1.93

Km

1.91

kms

1.84

 kilometre

1.78

 kilometer

1.68

Activations Density 0.052%

references to distances, specifically in kilometers

No Comments

No Known Activations