INDEX

Explanations

references to categories, coding, and document structure within responses or articles

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

cor

-0.48

vit

-0.46

jstor

-0.45

verige

-0.42

нив

-0.39

del

-0.38

 version

-0.37

ché

-0.36

 type

-0.36

 MERCHANTABILITY

-0.36

POSITIVE LOGITS

Portale

1.19

 ErrIntOverflow

1.07

subpackage

1.02

 незавершена

0.97

Portály

0.86

 autorytatywna

0.86

 BoxFit

0.86

Хьажоргаш

0.83

IUrlHelper

0.82

mybatisplus

0.80

Activations Density 0.655%

references to categories, coding, and document structure within responses or articles

No Comments

No Known Activations