INDEX

Explanations

coding constructs related to API requests and responses

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

 kỹ

-0.48

colorPrimary

-0.47

uração

-0.46

 sich

-0.46

urlar

-0.44

zuf

-0.44

 standar

-0.43

 arco

-0.42

 تضيفلها

-0.42

ген

-0.40

POSITIVE LOGITS

mybatisplus

0.87

 Italijanski

0.74

#+#

0.73

 تانيه

0.68

 Audiodateien

0.68

 beginnetje

0.67

 disambiguazione

0.66

 JpaRepository

0.64

 Whig

0.63

Życiorys

0.63

Activations Density 0.059%

coding constructs related to API requests and responses

No Comments

No Known Activations