INDEX

Explanations

technical terms, parameters, and values related to data structures or programming elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 isKindOfClass

-0.40

entrySet

-0.39

artigen

-0.38

</b>

-0.38

gic

-0.37

ChildIndex

-0.36

 reprises

-0.36

ñado

-0.36

Im

-0.36

 المعيارى

-0.35

POSITIVE LOGITS

 Infórmanos

0.91

 nahilalakip

0.81

httphttps

0.78

raszamy

0.77

SharedCtor

0.76

 EconPapers

0.76

contentLoaded

0.75

TestingModule

0.74

webElementXpaths

0.74

twimg

0.73

Activations Density 2.419%

technical terms, parameters, and values related to data structures or programming elements

No Comments

No Known Activations