INDEX

Explanations

phrases indicating location and presence in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

lyon

-0.53

esgue

-0.52

 Leto

-0.52

 Conducted

-0.52

 CONDU

-0.52

 metodi

-0.49

 Arta

-0.48

 march

-0.48

uchter

-0.48

 selectivity

-0.47

POSITIVE LOGITS

 ready

0.83

 صوتيه

0.71

tagHelperRunner

0.70

IntoConstraints

0.67

 there

0.66

richTextPanel

0.64

nonatomic

0.63

 bezig

0.63

 Roskov

0.63

 ProtoMessage

0.63

Activations Density 0.383%

phrases indicating location and presence in a specific context

No Comments

No Known Activations