INDEX

Explanations

mathematical terms and comparisons in a formal context, focusing on properties related to sets, values, and relationships between integers

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 للاسماء

-0.55

+#+#

-0.52

RegressionTest

-0.51

 &___

-0.47

ſelf

-0.47

Personensuche

-0.46

AutoScale

-0.45

 Theſe

-0.44

Зноскі

-0.43

rungsseite

-0.41

POSITIVE LOGITS

rigkeit

0.43

typeparam

0.40

entgen

0.40

 تانيه

0.38

endcsname

0.38

dific

0.38

 PROTE

0.38

 FLUID

0.37

 CONTRA

0.37

 GENE

0.37

Activations Density 1.851%

mathematical terms and comparisons in a formal context, focusing on properties related to sets, values, and relationships between integers

No Known Activations