INDEX

Explanations

references to the efficiency parameter in photon generation and interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anso

-0.77

<em>

-0.74

bro

-0.73

-0.71

-0.69

 Lombardo

-0.69

 jawa

-0.67

Bres

-0.66

ūras

-0.64

bro

-0.64

POSITIVE LOGITS

Eta

1.45

eta

1.41

eta

1.41

ETA

1.34

Eta

1.34

Etape

1.31

η

1.23

η

1.20

PerformLayout

0.95

 <=",

0.95

Activations Density 0.018%

references to the efficiency parameter in photon generation and interaction

No Comments

No Known Activations