INDEX

Explanations

references to components in programming and frameworks

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

 themſelves

-0.80

 myſelf

-0.78

 itſelf

-0.77

 ſever

-0.77

AndEndTag

-0.75

 Monfieur

-0.72

 pleaſure

-0.70

 Theſe

-0.69

 uſed

-0.69

 himſelf

-0.68

POSITIVE LOGITS

Component

3.11

 Component

2.19

COMPONENT

1.37

ListComponent

1.35

getComponent

1.29

component

1.28

 component

1.27

 COMPONENT

1.25

Components

1.24

FormComponent

1.23

Activations Density 0.081%

references to components in programming and frameworks

No Comments

No Known Activations