INDEX

Explanations

locations and geographic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

InvalidProtocol

-0.56

nexpected

-0.53

cknowled

-0.49

hazi

-0.49

IsContent

-0.49

כט

-0.49

อะไร

-0.48

rig

-0.48

Évaluation

-0.47

AddTagHelper

-0.47

POSITIVE LOGITS

NewUrlParser

0.82

IBarButtonItem

0.64

 noqa

0.62

contentLoaded

0.61

paramref

0.60

RefNanny

0.58

CGSize

0.58

CloseOperation

0.56

 wikipagina

0.55

multer

0.55

Activations Density 0.572%

locations and geographic references

No Comments

No Known Activations