INDEX

Explanations

negations or phrases expressing absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

oubliez

-0.51

 scuro

-0.47

 KeyEvent

-0.46

 foncé

-0.46

 intptr

-0.45

вані

-0.45

 arasındaki

-0.44

 görül

-0.43

 transfieras

-0.42

 sfondo

-0.42

POSITIVE LOGITS

esterday

0.84

BagLayout

0.76

 مشين

0.66

Geplaatst

0.65

});*/

0.64

InstanceState

0.62

fwrite

0.60

ätzt

0.59

enumi

0.59

copg

0.59

Activations Density 0.116%

negations or phrases expressing absence

No Comments

No Known Activations