INDEX

Explanations

terms related to mathematical definitions and proofs

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AspNetCore

-0.50

vũ

-0.49

 murid

-0.47

 const

-0.47

tom

-0.46

min

-0.46

UNSIGNED

-0.46

丁目

-0.46

-0.45

Portail

-0.45

POSITIVE LOGITS

AndroidJUnit

0.68

 Alcott

0.67

✭✭

0.63

Javadoc

0.62

^(@)

0.61

quy

0.61

achau

0.61

 demurrer

0.59

sizeCache

0.59

 isolada

0.59

Activations Density 0.339%

terms related to mathematical definitions and proofs

No Comments

No Known Activations