INDEX

Explanations

phrases indicating spatial relationships or distributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Cæsar

-0.73

 initComponents

-0.71

bbene

-0.69

 Ruman

-0.66

NPY

-0.64

scp

-0.64

LPS

-0.64

 NIOS

-0.63

 CURIAM

-0.63

ACI

-0.63

POSITIVE LOGITS

the

1.47

1.06

an

0.94

 these

0.84

 some

0.83

our

0.83

its

0.81

 those

0.81

 this

0.79

 your

0.79

Activations Density 0.328%

phrases indicating spatial relationships or distributions

No Comments

No Known Activations