INDEX

Explanations

numerical codes or identifiers, likely related to structured data or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

AsUp

-0.91

 ་་

-0.90

 itſelf

-0.90

 Theſe

-0.86

 myſelf

-0.84

 ―――――

-0.84

 فريبيس

-0.83

 saites

-0.80

 Wikimedijinoj

-0.79

 themſelves

-0.77

POSITIVE LOGITS

RequestMapping

0.60

ไ

0.60

“

0.58

the

0.56

<strong>

0.55

querySelectorAll

0.55

<em>

0.54

0.53

you

0.53

Activations Density 0.346%

numerical codes or identifiers, likely related to structured data or programming contexts

No Comments

No Known Activations