INDEX

Explanations

relationships involving mathematical norms and their representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

حياته

-0.69

 Leyden

-0.62

 exact

-0.61

useNewUrlParser

-0.61

Jab

-0.61

 Carden

-0.57

Caz

-0.57

jare

-0.57

 متعلقه

-0.56

ltä

-0.56

POSITIVE LOGITS

\|

1.63

$\|

1.58

}\|

1.53

\|\

1.51

\|

1.42

\|^{

1.21

\|_{\

1.03

\|_{

0.99

∥

0.95

 Norwalk

0.84

Activations Density 0.372%

relationships involving mathematical norms and their representations

No Comments

No Known Activations