INDEX

Explanations

articles and nouns that suggest the presence of an object or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

więcej

-0.35

}}^

-0.33

abestanden

-0.32

hånd

-0.31

++]=

-0.29

PositiveButton

-0.29

 Wikimedijinoj

-0.29

 tùy

-0.29

 powiet

-0.28

 puțin

-0.28

POSITIVE LOGITS

webElementXpaths

0.67

 betweenstory

0.64

 Италијани

0.63

 ioutil

0.52

 Photocase

0.52

uxxxx

0.51

 queſto

0.50



0.50

 purpoſe

0.49

 snippetHide

0.49

Activations Density 0.711%

articles and nouns that suggest the presence of an object or entity

No Comments

No Known Activations