INDEX

Explanations

structures related to JSON or object definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 voisins

-0.64

 mengenakan

-0.59

 médicas

-0.58

 nuages

-0.58

 épu

-0.58

 commerciaux

-0.57

 économies

-0.57

 kroppen

-0.56

Atsauces

-0.56

 fabbrica

-0.56

POSITIVE LOGITS

 “...

0.83

...(

0.81

“...

0.81

$:

0.80

 "...

0.75

“…

0.73

'...

0.73

[`

0.72

__;

0.72

...}

0.71

Activations Density 0.175%

structures related to JSON or object definitions

No Comments

No Known Activations