INDEX

Explanations

terms related to graphic rendering or image processing

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

:✨

-0.76

expandindo

-0.71

цездатний

-0.68

mobileqq

-0.63

 nakalista

-0.61

Datuak

-0.60

Демографія

-0.59

 ―――――

-0.59

 Theſe

-0.58

 censiti

-0.58

POSITIVE LOGITS

gr

0.73

Gr

0.66

 grinding

0.65

Gr

0.62

 queries

0.51

 sleep

0.49

gru

0.49

nic

0.49

gr

0.48

Nic

0.48

Activations Density 0.290%

terms related to graphic rendering or image processing

No Comments

No Known Activations