INDEX

Explanations

superlative descriptors of entities or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

oldo

-0.47

imshow

-0.43

 Dobson

-0.42

 nastro

-0.42

zka

-0.41

setViewportView

-0.40

 Anexo

-0.40

ВС

-0.39

jednoc

-0.39

örös

-0.38

POSITIVE LOGITS

 ever

0.91

iest

0.85

ziest

0.81

greatest

0.80

 imaginable

0.80

 fastest

0.79

 finest

0.79

 EVER

0.78

 greatest

0.77

EVER

0.76

Activations Density 0.190%

superlative descriptors of entities or experiences

No Comments

No Known Activations