INDEX

Explanations

terms associated with crystals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ReusableCell

-0.77

apimachinery

-0.72

 שוליים

-0.62

зви

-0.59

 Pont

-0.59

Роди

-0.58

Câ

-0.58

󠁢

-0.58

órc

-0.58

Ộ

-0.57

POSITIVE LOGITS

timestamp

0.78

 crystal

0.72

Crystal

0.70

 flushed

0.69

crystal

0.68

 flush

0.68

Mel

0.67

 timestamp

0.67

 Crystal

0.66

Sal

0.66

Activations Density 0.069%

terms associated with crystals

No Comments

No Known Activations