INDEX

Explanations

mathematical expressions and notations related to structured data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

expandindo

-0.49

 Manu

-0.48

MPR

-0.48

 resourceCulture

-0.47

 AppCompat

-0.46

mphony

-0.46

 Helio

-0.45

 Daven

-0.45

SMP

-0.44

 Chico

-0.44

POSITIVE LOGITS

AZ

1.51

az

1.45

AZ

1.45

Az

1.42

IZ

1.38

EZ

1.35

EZ

1.32

Az

1.31

az

1.31

ez

1.29

Activations Density 0.451%

mathematical expressions and notations related to structured data

No Comments

No Known Activations