INDEX

Explanations

references to the term "Chi"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.69

-0.68

-0.67

the

-0.63

↵

-0.60

-0.59

-0.57

in

-0.54

 grand

-0.53

***

-0.53

POSITIVE LOGITS

ſelves

1.43

 myſelf

1.40

Efq

1.39

 Theſe

1.33

ſelf

1.33

 purpoſe

1.29

 незавершена

1.29

 itſelf

1.29

 GenerationType

1.26

 becauſe

1.25

Activations Density 0.213%

references to the term "Chi"

No Comments

No Known Activations

references to the term "Chi"

No Comments

No Known Activations