INDEX

Explanations

technical terms and error messages related to information processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

expandindo

-0.71

 both

-0.46

fred

-0.43

'=>'

-0.43

 fossero

-0.42

parral

-0.42

BeforeEach

-0.41

both

-0.41

an

-0.41

Both

-0.41

POSITIVE LOGITS

onOptions

0.81

клопе

0.73

 <=",

0.72

Geografie

0.70

 Exactos

0.66

onActivityResult

0.65

RegistryLite

0.64

 NgModule

0.63

Havolalar

0.63

RectangleBorder

0.62

Activations Density 0.381%

technical terms and error messages related to information processing

No Comments

No Known Activations