INDEX

Explanations

references to columns in structured data formats, particularly in relation to graphical user interfaces or data organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 portato

-0.50

 naturales

-0.49

vru

-0.48

 naturali

-0.47

lji

-0.46

 portare

-0.46

 morire

-0.44

resource

-0.44

 partecipare

-0.44

 huella

-0.43

POSITIVE LOGITS

 tabs

0.73

 pins

0.73

 columns

0.72

 plugs

0.64

 mods

0.62

tabs

0.59

 cols

0.59

parsedMessage

0.59

 dots

0.58

 Guns

0.58

Activations Density 0.194%

references to columns in structured data formats, particularly in relation to graphical user interfaces or data organization

No Comments

No Known Activations